mailitics

Category: deep-dives

  • Do You Really Need a Foundation Model?

    Do You Really Need a Foundation Model? LLM or custom model: how should you choose the right solution? The post Do You Really Need a Foundation Model? appeared first on Towards Data Science. Vincent Vandenbussche Go to original source

  • What Can the History of Data Tell Us About the Future of AI?

    What Can the History of Data Tell Us About the Future of AI? A 40-Year Look at Data, Business Models, and the Forces Shaping Intelligent Systems The post What Can the History of Data Tell Us About the Future of AI? appeared first on Towards Data Science. Steve Hedden Go to original source

  • Dynamic Inventory Optimization with Censored Demand

    Dynamic Inventory Optimization with Censored Demand A sequential decision framework with Bayesian learning The post Dynamic Inventory Optimization with Censored Demand appeared first on Towards Data Science. Mert Ersoz Go to original source

  • Building a Сustom MCP Chatbot

    Building a Сustom MCP Chatbot Understanding all the details of the model context protocol The post Building a Сustom MCP Chatbot appeared first on Towards Data Science. Mariya Mansurova Go to original source

  • Scene Understanding in Action: Real-World Validation of Multimodal AI Integration

    Scene Understanding in Action: Real-World Validation of Multimodal AI Integration A deep dive into real-world case studies: from indoor space and urban streets to world-famous landmarks The post Scene Understanding in Action: Real-World Validation of Multimodal AI Integration appeared first on Towards Data Science. Eric Chung Go to original source

  • Evaluation-Driven Development for LLM-Powered Products: Lessons from Building in Healthcare

    Evaluation-Driven Development for LLM-Powered Products: Lessons from Building in Healthcare How metrics and monitoring combine with human expertise to build trustworthy AI in healthcare. The post Evaluation-Driven Development for LLM-Powered Products: Lessons from Building in Healthcare appeared first on Towards Data Science. Robert Martin-Short Go to original source

  • Work Data Is the Next Frontier for GenAI

    Work Data Is the Next Frontier for GenAI 9 reasons why work data is the single most valuable data source for LLM training, uniquely capable of propelling LLM performance to unprecedented heights. The post Work Data Is the Next Frontier for GenAI appeared first on Towards Data Science. Zsombor Varnagy-Toth Go to original source

  • How to Fine-Tune Small Language Models to Think with Reinforcement Learning

    How to Fine-Tune Small Language Models to Think with Reinforcement Learning A visual tour and from-scratch guide to train GRPO reasoning models in PyTorch The post How to Fine-Tune Small Language Models to Think with Reinforcement Learning appeared first on Towards Data Science. Avishek Biswas Go to original source

  • Run Your Python Code up to 80x Faster Using the Cython Library

    Run Your Python Code up to 80x Faster Using the Cython Library A four-step plan for C language speed where it matters most The post Run Your Python Code up to 80x Faster Using the Cython Library appeared first on Towards Data Science. Thomas Reid Go to original source

  • Build Algorithm-Agnostic ML Pipelines in a Breeze

    Build Algorithm-Agnostic ML Pipelines in a Breeze The framework is now an open-source Python package for streamlined ML workflows The post Build Algorithm-Agnostic ML Pipelines in a Breeze appeared first on Towards Data Science. Mena Wang Go to original source

  • Explainable Anomaly Detection with RuleFit: An Intuitive Guide

    Explainable Anomaly Detection with RuleFit: An Intuitive Guide Creating interpretable rules to characterize the identified anomalies The post Explainable Anomaly Detection with RuleFit: An Intuitive Guide appeared first on Towards Data Science. Shuai Guo Go to original source

  • GraphRAG in Action: A Simple Agent for Know-Your-Customer Investigations

    GraphRAG in Action: A Simple Agent for Know-Your-Customer Investigations This blog post provides a hands-on guide for AI engineers and developers on how to build an initial KYC agent prototype with the OpenAI Agents SDK. We’ll explore how to equip our agent with a suite of tools (including MCP Server tools) to uncover and investigate potential…

  • Taking ResNet to the Next Level

    Taking ResNet to the Next Level Understanding how ResNeXt improves upon ResNet, with a comprehensive PyTorch implementation guide The post Taking ResNet to the Next Level appeared first on Towards Data Science. Muhammad Ardi Go to original source

  • Four AI Minds in Concert: A Deep Dive into Multimodal AI Fusion

    Four AI Minds in Concert: A Deep Dive into Multimodal AI Fusion Introduction: From System Architecture to Algorithmic Execution In my previous article, I explored the architectural foundations of the VisionScout multimodal AI system, tracing its evolution from a simple object detection model into a modular framework. There, I highlighted how careful layering, module boundaries,…

  • Revisiting Benchmarking of Tabular Reinforcement Learning Methods

    Revisiting Benchmarking of Tabular Reinforcement Learning Methods Introducing a modular framework and improving model performance. The post Revisiting Benchmarking of Tabular Reinforcement Learning Methods appeared first on Towards Data Science. Oliver S Go to original source

  • Prescriptive Modeling Makes Causal Bets – Whether You Know it or Not!

    Prescriptive Modeling Makes Causal Bets – Whether You Know it or Not! An explanation of the causal assumption implicit in prescriptive modeling and how to satisfy it. The post Prescriptive Modeling Makes Causal Bets – Whether You Know it or Not! appeared first on Towards Data Science. Jarom Hulet Go to original source

  • A Developer’s Guide to Building Scalable AI: Workflows vs Agents

    A Developer’s Guide to Building Scalable AI: Workflows vs Agents A practical guide to choosing between AI agents and workflows for production systems, covering the hidden costs, architectural trade-offs, and decision framework that can save you thousands in deployment mistakes. Includes real-world examples and a scoring system to determine which approach fits your specific use…

  • A Caching Strategy for Identifying Bottlenecks on the Data Input Pipeline

    A Caching Strategy for Identifying Bottlenecks on the Data Input Pipeline PyTorch model performance analysis and optimization — Part 8 The post A Caching Strategy for Identifying Bottlenecks on the Data Input Pipeline appeared first on Towards Data Science. Chaim Rand Go to original source

  • Data Science: From School to Work, Part V

    Data Science: From School to Work, Part V How to profile your Python project The post Data Science: From School to Work, Part V appeared first on Towards Data Science. Vincent Margot Go to original source

  • Agentic AI: Implementing Long-Term Memory

    Agentic AI: Implementing Long-Term Memory The problem and current solutions The post Agentic AI: Implementing Long-Term Memory appeared first on Towards Data Science. Ida Silfverskiöld Go to original source

  • Build Multi-Agent Apps with OpenAI’s Agent SDK

    Build Multi-Agent Apps with OpenAI’s Agent SDK Creating multi-agent apps is simple with this open-source SDK, and it can be used with any OpenAI-compatible LLM The post Build Multi-Agent Apps with OpenAI’s Agent SDK appeared first on Towards Data Science. Alan Jones Go to original source

  • Programming, Not Prompting: A Hands-On Guide to DSPy

    Programming, Not Prompting: A Hands-On Guide to DSPy A practical deep dive into declarative AI programming The post Programming, Not Prompting: A Hands-On Guide to DSPy appeared first on Towards Data Science. Mariya Mansurova Go to original source

  • Building A Modern Dashboard with Python and Taipy

    Building A Modern Dashboard with Python and Taipy A guide to building a front-end data application. The post Building A Modern Dashboard with Python and Taipy appeared first on Towards Data Science. Thomas Reid Go to original source

  • Beyond Model Stacking: The Architecture Principles That Make Multimodal AI Systems Work

    Beyond Model Stacking: The Architecture Principles That Make Multimodal AI Systems Work Transforming Independent Models into Collaborative Intelligence The post Beyond Model Stacking: The Architecture Principles That Make Multimodal AI Systems Work appeared first on Towards Data Science. Eric Chung Go to original source

  • LLM-as-a-Judge: A Practical Guide

    LLM-as-a-Judge: A Practical Guide How to Scale LLM Evaluations Beyond Manual Review The post LLM-as-a-Judge: A Practical Guide appeared first on Towards Data Science. Shuai Guo Go to original source

  • Beyond Code Generation: Continuously Evolve Text with LLMs

    Beyond Code Generation: Continuously Evolve Text with LLMs Long-running content evolution and an introduction to result analysis The post Beyond Code Generation: Continuously Evolve Text with LLMs appeared first on Towards Data Science. Julian Mendel Go to original source

  • A Multi-Agent SQL Assistant You Can Trust with Human-in-Loop Checkpoint & LLM Cost Control

    A Multi-Agent SQL Assistant You Can Trust with Human-in-Loop Checkpoint & LLM Cost Control Your very own SQL assistant built with Streamlit, SQLite, & CrewAI The post A Multi-Agent SQL Assistant You Can Trust with Human-in-Loop Checkpoint & LLM Cost Control appeared first on Towards Data Science. Alle Sravani Go to original source

  • A Practical Starters’ Guide to Causal Structure Learning with Bayesian Methods in Python

    A Practical Starters’ Guide to Causal Structure Learning with Bayesian Methods in Python Learn Causal Structures and make inferences with Bayesian Methods: Python Tutorial The post A Practical Starters’ Guide to Causal Structure Learning with Bayesian Methods in Python appeared first on Towards Data Science. Erdogan Taskesen Go to original source

  • Regularisation: A Deep Dive into Theory, Implementation, and Practical Insights

    Regularisation: A Deep Dive into Theory, Implementation, and Practical Insights A detailed guide on controlling overfitting and increasing the stability of your models. The post Regularisation: A Deep Dive into Theory, Implementation, and Practical Insights appeared first on Towards Data Science. Sourav Mohile Go to original source

  • Can AI Truly Develop a Memory That Adapts Like Ours?

    Can AI Truly Develop a Memory That Adapts Like Ours? Exploring Titans: A new architecture equipping LLMs with human-inspired memory that learns and updates itself during test-time. The post Can AI Truly Develop a Memory That Adapts Like Ours? appeared first on Towards Data Science. Moulik Gupta Go to original source

  • 10,000x Faster Bayesian Inference: Multi-GPU SVI vs. Traditional MCMC

    10,000x Faster Bayesian Inference: Multi-GPU SVI vs. Traditional MCMC Using GPU acceleration to speed up Bayesian Inference from months to minutes… The post 10,000x Faster Bayesian Inference: Multi-GPU SVI vs. Traditional MCMC appeared first on Towards Data Science. Derek Tran Go to original source

  • A Bird’s-Eye View of Linear Algebra: Measure of a Map — Determinants

    A Bird’s-Eye View of Linear Algebra: Measure of a Map — Determinants We roll up our sleeves and start to deal with matrices The post A Bird’s-Eye View of Linear Algebra: Measure of a Map — Determinants appeared first on Towards Data Science. Rohit Pandey Go to original source

  • Prescriptive Modeling Unpacked: A Complete Guide to Intervention With Bayesian Modeling.

    Prescriptive Modeling Unpacked: A Complete Guide to Intervention With Bayesian Modeling. Learn how to move beyond prediction and actively make intervention through prescriptive modeling. This in-depth guide walks you through Bayesian approaches to system intervention, with practical examples in predictive maintenance. The post Prescriptive Modeling Unpacked: A Complete Guide to Intervention With Bayesian Modeling. appeared…

  • Building a Modern Dashboard with Python and Gradio

    Building a Modern Dashboard with Python and Gradio Data insights made simple The post Building a Modern Dashboard with Python and Gradio appeared first on Towards Data Science. Thomas Reid Go to original source

  • Landing your First Machine Learning Job: Startup vs Big Tech vs Academia

    Landing your First Machine Learning Job: Startup vs Big Tech vs Academia A practical guide to landing your first Machine Learning job across startups, big tech, and academia. The post Landing your First Machine Learning Job: Startup vs Big Tech vs Academia appeared first on Towards Data Science. Piero Paialunga Go to original source

  • Vision Transformer on a Budget

    Vision Transformer on a Budget Introduction The vanilla ViT is problematic. If you take a look at the original ViT paper [1], you’ll notice that although this deep learning model proved to work extremely well, it requires hundreds of millions of labeled training images to achieve this.  Well, that’s a lot.  This requirement of an enormous…

  • Agentic RAG Applications: Company Knowledge Slack Agents

    Agentic RAG Applications: Company Knowledge Slack Agents Lessons learnt using LlamaIndex and Modal The post Agentic RAG Applications: Company Knowledge Slack Agents appeared first on Towards Data Science. Ida Silfverskiöld Go to original source

  • A Bird’s Eye View of Linear Algebra: The Basics

    A Bird’s Eye View of Linear Algebra: The Basics We think basis-free, we write basis-free, but when the chips are down we close the office door and compute with matrices like fury. The post A Bird’s Eye View of Linear Algebra: The Basics appeared first on Towards Data Science. Rohit Pandey Go to original source

  • From Data to Stories: Code Agents for KPI Narratives

    From Data to Stories: Code Agents for KPI Narratives HuggingFace’s smolagents framework in action The post From Data to Stories: Code Agents for KPI Narratives appeared first on Towards Data Science. Mariya Mansurova Go to original source

  • Detecting Malicious URLs Using LSTM and Google’s BERT Models

    Detecting Malicious URLs Using LSTM and Google’s BERT Models A progressive approach to implementing AI-powered webpage detection applications into production The post Detecting Malicious URLs Using LSTM and Google’s BERT Models appeared first on Towards Data Science. Toluwase Babalola Go to original source

  • Bayesian Optimization for Hyperparameter Tuning of Deep Learning Models

    Bayesian Optimization for Hyperparameter Tuning of Deep Learning Models Explore how Bayesian Optimization outperforms Grid Search in efficiency and performance over binary classification tasks. The post Bayesian Optimization for Hyperparameter Tuning of Deep Learning Models appeared first on Towards Data Science. Kuriko Iwai Go to original source

  • Reinforcement Learning Made Simple: Build a Q-Learning Agent in Python

    Reinforcement Learning Made Simple: Build a Q-Learning Agent in Python Inspired by AlphaGo’s Move 37 — learn how agents explore, exploit, and win The post Reinforcement Learning Made Simple: Build a Q-Learning Agent in Python appeared first on Towards Data Science. Sarah Schürch Go to original source

  • How to Reduce Your Power BI Model Size by 90%

    How to Reduce Your Power BI Model Size by 90% Have you ever wondered what makes Power BI so fast and powerful when it comes to performance? Learn on a real-life example about data model optimization and general rules for reducing data model The post How to Reduce Your Power BI Model Size by 90%…

  • How to Generate Synthetic Data: A Comprehensive Guide Using Bayesian Sampling and Univariate Distributions

    How to Generate Synthetic Data: A Comprehensive Guide Using Bayesian Sampling and Univariate Distributions Data makes the engine run in many organisations. But what if the number of observations is too low or there is only expert knowledge? I will demonstrate how to generate synthetic data with applications in predictive maintenance. The post How to…

  • Estimating Product-Level Price Elasticities Using Hierarchical Bayesian

    Estimating Product-Level Price Elasticities Using Hierarchical Bayesian Using one model to personalize ML results The post Estimating Product-Level Price Elasticities Using Hierarchical Bayesian appeared first on Towards Data Science. Derek Tran Go to original source

  • Google’s AlphaEvolve: Getting Started with Evolutionary Coding Agents

    Google’s AlphaEvolve: Getting Started with Evolutionary Coding Agents Introduction AlphaEvolve [1] is a promising new coding agent by Google’s DeepMind. Let’s look at what it is and why it is generating hype. Much of the Google paper is on the claim that AlphaEvolve is facilitating novel research through its ability to improve code until it solves…

  • Multiple Linear Regression Analysis

    Multiple Linear Regression Analysis Implementation of multiple linear regression on real data: Assumption checks, model evaluation, and interpretation of results using Python. The post Multiple Linear Regression Analysis appeared first on Towards Data Science. JUNIOR JUMBONG Go to original source

  • Building AI Applications in Ruby

    Building AI Applications in Ruby This is the second in a multi-part series on creating web applications with generative AI integration. Part 1 focused on explaining the AI stack and why the application layer is the best place in the stack to be. Check it out here. Table of Contents Introduction I thought spas were supposed…

  • How to Set the Number of Trees in Random Forest

    How to Set the Number of Trees in Random Forest Scientific publication T. M. Lange, M. Gültas, A. O. Schmitt & F. Heinrich (2025). optRF: Optimising random forest stability by determining the optimal number of trees. BMC bioinformatics, 26(1), 95. Follow this LINK to the original publication. Random Forest — A Powerful Tool for Anyone…

  • Understanding Random Forest using Python (scikit-learn)

    Understanding Random Forest using Python (scikit-learn) Decision trees are a popular supervised learning algorithm with benefits that include being able to be used for both regression and classification as well as being easy to interpret. However, decision trees aren’t the most performant algorithm and are prone to overfitting due to small variations in the training…

  • 🚪🚪🐐 Lessons in Decision Making from the Monty Hall Problem

    🚪🚪🐐 Lessons in Decision Making from the Monty Hall Problem The Monty Hall Problem is a well-known brain teaser from which we can learn important lessons in Decision Making that are useful in general and in particular for data scientists. If you are not familiar with this problem, prepare to be perplexed . If you…

  • Rethinking the Environmental Costs of Training AI — Why We Should Look Beyond Hardware

    Rethinking the Environmental Costs of Training AI — Why We Should Look Beyond Hardware Summary of This Study Hardware choices – specifically hardware type and its quantity – along with training time, have a significant positive impact on energy, water, and carbon footprints during AI model training, whereas architecture-related factors do not. The interaction between…

  • Empowering LLMs to Think Deeper by Erasing Thoughts

    Empowering LLMs to Think Deeper by Erasing Thoughts Introduction Recent large language models (LLMs) — such as OpenAI’s o1/o3, DeepSeek’s R1 and Anthropic’s Claude 3.7 — demonstrate that allowing the model to think deeper and longer at test time can significantly enhance model’s reasoning capability. The core approach underlying their deep thinking capability is called…

  • Running Python Programs in Your Browser

    Running Python Programs in Your Browser In recent years, WebAssembly (often abbreviated as WASM) has emerged as an interesting technology that extends web browsers’ capabilities far beyond the traditional realms of HTML, CSS, and JavaScript.  As a Python developer, one particularly exciting application is the ability to run Python code directly in the browser. In this…

  • How Not to Write an MCP Server

    How Not to Write an MCP Server I recently had the chance to create an MCP server for an observability application in order to provide the AI agent with dynamic code analysis capabilities. Because of its potential to transform applications, MCP is a technology I’m even more ecstatic about than I originally was about genAI…

  • Clustering Eating Behaviors in Time: A Machine Learning Approach to Preventive Health

    Clustering Eating Behaviors in Time: A Machine Learning Approach to Preventive Health It’s well known that what we eat matters — but what if when and how often we eat matters just as much? In the midst of ongoing scientific debate around the benefits of intermittent fasting, this question becomes even more intriguing. As someone passionate about machine learning and healthy living,…

  • Model Compression: Make Your Machine Learning Models Lighter and Faster

    Model Compression: Make Your Machine Learning Models Lighter and Faster Introduction Whether you’re preparing for interviews or building Machine Learning systems at your job, model compression has become a must-have skill. In the era of LLMs, where models are getting larger and larger, the challenges around compressing these models to make them more efficient, smaller,…

  • A Practical Guide to BERTopic for Transformer-Based Topic Modeling

    A Practical Guide to BERTopic for Transformer-Based Topic Modeling Topic modeling has a wide range of use cases in the natural language processing (NLP) domain, such as document tagging, survey analysis, and content organization. It falls under the realm of unsupervised learning technique, making it a very cost-effective technique that reduces the resources required to…

  • The Total Derivative: Correcting the Misconception of Backpropagation’s Chain Rule

    The Total Derivative: Correcting the Misconception of Backpropagation’s Chain Rule This article uses concepts from this brilliant paper. For a deeper understanding of the mathematics please refer to the paper. Here we try to present the math in a more intuitive and explicit way, with some important nuances highlighted. 1 Introduction Discussions about Backpropagation often…

  • The CNN That Challenges ViT

    The CNN That Challenges ViT Introduction The invention of ViT (Vision Transformer) causes us to think that CNNs are obsolete.  But is this really true? It is widely believed that the impressive performance of ViT comes primarily from its transformer-based architecture. However, researchers from Meta argued that it’s not entirely true. If we take a closer…

  • Fine-Tuning vLLMs for Document Understanding

    Fine-Tuning vLLMs for Document Understanding In this article, I discuss how you can fine-tune VLMs (visual large language models, often called vLLMs) like Qwen 2.5 VL 7B. I will introduce you to a dataset of handwritten digits, which the base version of Qwen 2.5 VL struggles with. We will then inspect the dataset, annotate it,…

  • Attaining LLM Certainty with AI Decision Circuits

    Attaining LLM Certainty with AI Decision Circuits The promise of AI agents has taken the world by storm. Agents can interact with the world around them, write articles (not this one though), take actions on your behalf, and generally make the difficult part of automating any task easy and approachable.  Agents take aim at the most…

  • Step-by-Step Guide to Build and Deploy an LLM-Powered Chat with Memory in Streamlit

    Step-by-Step Guide to Build and Deploy an LLM-Powered Chat with Memory in Streamlit In this post, I’ll show you step by step how to build and deploy a chat powered with LLM — Gemini — in Streamlit and monitor the API usage on Google Cloud Console. Streamlit is a Python framework that makes it super easy to turn your…

  • Modern GUI Applications for Computer Vision in Python

    Modern GUI Applications for Computer Vision in Python Introduction I’m a huge fan of interactive visualizations. As a computer vision engineer, I deal almost daily with image processing related tasks and more often than not I am iterating on a problem where I need visual feedback to make decisions. Let’s think of a very simple image…

  • LLM Evaluations: from Prototype to Production

    LLM Evaluations: from Prototype to Production Evaluation is the cornerstone of any machine learning product. Investing in quality measurement delivers significant returns. Let’s explore the potential business benefits. As management consultant and writer Peter Drucker once said, “If you can’t measure it, you can’t improve it.” Building a robust evaluation system helps you identify areas…

  • Government Funding Graph RAG

    Government Funding Graph RAG In this article, I present my latest open-source project — Government Funding Graph. The inspiration for this project came from a desire to make better tooling for grant writing, namely to suggest research topics, funding bodies, research institutions, and researchers. I have made Innovate UK grant applications in the past, so I have…

  • Data Science: From School to Work, Part IV

    Data Science: From School to Work, Part IV Introduction Let’s start with a simple example that will appeal to most of us. If you want to check if the blinkers of your car are working properly, you sit in the car, turn on the ignition and test a turn signal to see if the front…

  • MapReduce: How It Powers Scalable Data Processing

    MapReduce: How It Powers Scalable Data Processing In this article, I’ll give a brief introduction to the MapReduce programming model. Hopefully after reading this, you leave with a solid intuition of what MapReduce is, the role it plays in scalable data processing, and how to recognize when it can be applied to optimize a computational…

  • Google’s New AI System Outperforms Physicians in Complex Diagnoses

    Google’s New AI System Outperforms Physicians in Complex Diagnoses Imagine going to the doctor with a baffling set of symptoms. Getting the right diagnosis quickly is crucial, but sometimes even experienced physicians face challenges piecing together the puzzle. Sometimes it might not be something serious at all; others a deep investigation might be required. No…

  • An LLM-Based Workflow for Automated Tabular Data Validation 

    An LLM-Based Workflow for Automated Tabular Data Validation  This article is part of a series of articles on automating data cleaning for any tabular dataset: Effortless Spreadsheet Normalisation With LLM You can test the feature described in this article on your own dataset using the CleanMyExcel.io service, which is free and requires no registration. What…

  • Learnings from a Machine Learning Engineer — Part 6: The Human Side

    Learnings from a Machine Learning Engineer — Part 6: The Human Side In my previous articles, I have spent a lot of time talking about the technical aspects of an Image Classification problem from data collection, model evaluation, performance optimization, and a detailed look at model training. These elements require a certain degree of in-depth expertise, and they (usually) have well-defined…

  • The Invisible Revolution: How Vectors Are (Re)defining Business Success

    The Invisible Revolution: How Vectors Are (Re)defining Business Success In a world that focuses more on data, business leaders must understand vector thinking. At first, vectors may appear as complicated as algebra was in school, but they serve as a fundamental building block. Vectors are as essential as algebra for tasks like sharing a bill…

  • Deb8flow: Orchestrating Autonomous AI Debates with LangGraph and GPT-4o

    Deb8flow: Orchestrating Autonomous AI Debates with LangGraph and GPT-4o Introduction I’ve always been fascinated by debates—the strategic framing, the sharp retorts, and the carefully timed comebacks. Debates aren’t just entertaining; they’re structured battles of ideas, driven by logic and evidence. Recently, I started wondering: could we replicate that dynamic using AI agents—having them debate each…

  • How to Optimize your Python Program for Slowness

    How to Optimize your Python Program for Slowness Also available: A Rust version of this article. Everyone talks about making Python programs faster [1, 2, 3], but what if we pursue the opposite goal? Let’s explore how to make them slower — absurdly slower. Along the way, we’ll examine the nature of computation, the role of memory,…

  • Let’s Call a Spade a Spade: RDF and LPG — Cousins Who Should Learn to Live Together

    Let’s Call a Spade a Spade: RDF and LPG — Cousins Who Should Learn to Live Together In recent years, there has been a proliferation of articles, LinkedIn posts, and marketing materials presenting graph data models from different perspectives. This article will refrain from discussing specific products and instead focus solely on the comparison of…

  • Are We Watching More Ads Than Content? Analyzing YouTube Sponsor Data

    Are We Watching More Ads Than Content? Analyzing YouTube Sponsor Data I’m definitely not the only person who feels that YouTube sponsor segments have become longer and more frequent recently. Sometimes, I watch videos that seem to be trying to sell me something every couple of seconds. On one hand, it’s great that both small and…

  • Kernel Case Study: Flash Attention

    Kernel Case Study: Flash Attention The attention mechanism is at the core of modern day transformers. But scaling the context window of these transformers was a major challenge, and it still is even though we are in the era of a million tokens + context window (Qwen 2.5 [1]). There are both considerable compute and memory…

  • Agentic GraphRAG for Commercial Contracts

    Agentic GraphRAG for Commercial Contracts In every business, legal contracts are foundational documents that define the relationships, obligations, and responsibilities between parties. Whether it’s a partnership agreement, an NDA, or a supplier contract, these documents often contain critical information that drives decision-making, risk management, and compliance. However, navigating and extracting insights from these contracts can…

  • Agentic AI: Single vs Multi-Agent Systems

    Agentic AI: Single vs Multi-Agent Systems We’ve seen this shift the last few years from building rigid programming systems to natural language-driven workflows, all made possible with more advanced large language models. One of the interesting areas into these Agentic Ai systems is the difference between building a single versus multi-agent workflow, or perhaps the…

  • Understanding the Tech Stack Behind Generative AI

    Understanding the Tech Stack Behind Generative AI Understanding the Tech Stack Behind Generative AI When ChatGPT reached the one million user mark within five days and took off faster than any other technology in history, the world began to pay attention to artificial intelligence and AI applications. And so it continued apace. Since then, many…

  • The Art of Hybrid Architectures

    The Art of Hybrid Architectures In my previous article, I discussed how morphological feature extractors mimic the way biological experts visually assess images. This time, I want to go a step further and explore a new question:Can different architectures complement each other to build an AI that “sees” like an expert? Introduction: Rethinking Model Architecture…

  • From Physics to Probability: Hamiltonian Mechanics for Generative Modeling and MCMC

    From Physics to Probability: Hamiltonian Mechanics for Generative Modeling and MCMC Phase space of a nonlinear pendulum. Photo by the author. Hamiltonian mechanics is a way to describe how physical systems, like planets or pendulums, move over time, focusing on energy rather than just forces. By reframing complex dynamics through energy lenses, this 19th-century physics…

  • Uncertainty Quantification in Machine Learning with an Easy Python Interface

    Uncertainty Quantification in Machine Learning with an Easy Python Interface Uncertainty quantification (UQ) in a Machine Learning (ML) model allows one to estimate the precision of its predictions. This is extremely important for utilizing its predictions in real-world tasks. For instance, if a machine learning model is trained to predict a property of a material,…

  • Data-Driven March Madness Predictions

    Data-Driven March Madness Predictions March Madness is infamously unpredictable, a perfect storm where favorites tumble and underdogs rise to do the impossible. Every March, 64 men’s and 64 women’s College Basketball teams battle for glory, while millions of fans, analysts, and betting markets scramble to predict the outcomes. But the odds of picking a perfect…

  • Testing the Power of Multimodal AI Systems in Reading and Interpreting Photographs, Maps, Charts and More

    Testing the Power of Multimodal AI Systems in Reading and Interpreting Photographs, Maps, Charts and More Introduction It’s no news that artificial intelligence has made huge strides in recent years, particularly with the advent of multimodal models that can process and create both text and images, and some very new ones that also process and produce…

  • From Fuzzy to Precise: How a Morphological Feature Extractor Enhances AI’s Recognition Capabilities

    From Fuzzy to Precise: How a Morphological Feature Extractor Enhances AI’s Recognition Capabilities Introduction: Can AI really distinguish dog breeds like human experts? One day while taking a walk, I saw a fluffy white puppy and wondered, Is that a Bichon Frise or a Maltese? No matter how closely I looked, they seemed almost identical.…

  • No More Tableau Downtime: Metadata API for Proactive Data Health

    No More Tableau Downtime: Metadata API for Proactive Data Health In today’s world, the reliability of data solutions is everything. When we build dashboards and reports, one expects that the numbers reflected there are correct and up-to-date. Based on these numbers, insights are drawn and actions are taken. For any unforeseen reason, if the dashboards are…

  • Mastering the Poisson Distribution: Intuition and Foundations

    Mastering the Poisson Distribution: Intuition and Foundations You’ve probably used the normal distribution one or two times too many. We all have — It’s a true workhorse. But sometimes, we run into problems. For instance, when predicting or forecasting values, simulating data given a particular data-generating process, or when we try to visualise model output…

  • Mastering Hadoop, Part 3: Hadoop Ecosystem: Get the most out of your cluster

    Mastering Hadoop, Part 3: Hadoop Ecosystem: Get the most out of your cluster As we have already seen with the basic components (Part 1, Part 2), the Hadoop ecosystem is constantly evolving and being optimized for new applications. As a result, various tools and technologies have developed over time that make Hadoop more powerful and…

  • Nine Pico PIO Wats with Rust (Part 2)

    Nine Pico PIO Wats with Rust (Part 2) This is Part 2 of an exploration into the unexpected quirks of programming the Raspberry Pi Pico PIO with Micropython. If you missed Part 1, we uncovered four Wats that challenge assumptions about register count, instruction slots, the behavior of pull noblock, and smart yet cheap hardware.…

  • Essential Review Papers on Physics-Informed Neural Networks: A Curated Guide for Practitioners

    Essential Review Papers on Physics-Informed Neural Networks: A Curated Guide for Practitioners Staying on top of a fast-growing research field is never easy. I face this challenge firsthand as a practitioner in Physics-Informed Neural Networks (PINNs). New papers, be they algorithmic advancements or cutting-edge applications, are published at an accelerating pace by both academia and…

  • Mastering Hadoop, Part 2: Getting Hands-On — Setting Up and Scaling Hadoop

    Mastering Hadoop, Part 2: Getting Hands-On — Setting Up and Scaling Hadoop Now that we’ve explored Hadoop’s role and relevance, it’s time to show you how it works under the hood and how you can start working with it. To start, we are breaking down Hadoop’s core components — HDFS for storage, MapReduce for processing,…

  • From Fuzzy to Precise: How a Morphological Feature Extractor Enhances AI’s Recognition Capabilities

    From Fuzzy to Precise: How a Morphological Feature Extractor Enhances AI’s Recognition Capabilities Introduction: Can AI really distinguish dog breeds like human experts? One day while taking a walk, I saw a fluffy white puppy and wondered, Is that a Bichon Frise or a Maltese? No matter how closely I looked, they seemed almost identical.…

  • Image Captioning, Transformer Mode On

    Image Captioning, Transformer Mode On Introduction In my previous article, I discussed one of the earliest Deep Learning approaches for image captioning. If you’re interested in reading it, you can find the link to that article at the end of this one. Today, I would like to talk about Image Captioning again, but this time…

  • Generative AI Is Declarative

    Generative AI Is Declarative ChatGPT launched in 2022 and kicked off the Generative Ai boom. In the two years since, academics, technologists, and armchair experts have written libraries worth of articles on the technical underpinnings of generative AI and about the potential capabilities of both current and future generative AI models. Surprisingly little has been…

  • Unraveling Large Language Model Hallucinations

    Unraveling Large Language Model Hallucinations Introduction In a YouTube video titled Deep Dive into LLMs like ChatGPT, former Senior Director of AI at Tesla, Andrej Karpathy discusses the psychology of Large Language Models (LLMs) as emergent cognitive effects of the training pipeline. This article is inspired by his explanation of LLM hallucinations and the information presented in the…

  • Vision Transformers (ViT) Explained: Are They Better Than CNNs?

    Vision Transformers (ViT) Explained: Are They Better Than CNNs? 1. Introduction Ever since the introduction of the self-attention mechanism, Transformers have been the top choice when it comes to Natural Language Processing (NLP) tasks. Self-attention-based models are highly parallelizable and require substantially fewer parameters, making them much more computationally efficient, less prone to overfitting, and…

  • LLaDA: The Diffusion Model That Could Redefine Language Generation

    LLaDA: The Diffusion Model That Could Redefine Language Generation Introduction What if we could make language models think more like humans? Instead of writing one word at a time, what if they could sketch out their thoughts first, and gradually refine them? This is exactly what Large Language Diffusion Models (LLaDA) introduces: a different approach to…

  • Talking about Games

    Talking about Games Game theory is a field of research that is quite prominent in Economics but rather unpopular in other scientific disciplines. However, the concepts used in game theory can be of interest to a wider audience, including data scientists, statisticians, computer scientists or psychologists, to name just a few. This article is the…

  • Zero Human Code: What I Learned from Forcing AI to Build (and Fix) Its Own Code for 27 Straight Days

    Zero Human Code: What I Learned from Forcing AI to Build (and Fix) Its Own Code for 27 Straight Days 27 days, 1,700+ commits, 99,9% AI generated code The narrative around AI development tools has become increasingly detached from reality. YouTube is filled with claims of building complex applications in hours using AI assistants. The…