{"id":4626,"date":"2025-06-16T07:02:30","date_gmt":"2025-06-16T07:02:30","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2025\/06\/16\/2506-11043\/"},"modified":"2025-06-16T07:02:30","modified_gmt":"2025-06-16T07:02:30","slug":"2506-11043","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2025\/06\/16\/2506-11043\/","title":{"rendered":"A Framework for Non-Linear Attention via Modern Hopfield Networks"},"content":{"rendered":"<p>    A Framework for Non-Linear Attention via Modern Hopfield Networks<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n    <!-- no image --><br \/>\n \t<BR><br \/>\n<BR><\/BR><\/p>\n<div>arXiv:2506.11043v1 Announce Type: new<br \/>\nAbstract: In this work we propose an energy functional along the lines of Modern Hopfield Networks (MNH), the stationary points of which correspond to the attention due to Vaswani et al. [12], thus unifying both frameworks. The minima of this landscape form &#8220;context wells&#8221; &#8211; stable configurations that encapsulate the contextual relationships among tokens. A compelling picture emerges: across $n$ token embeddings an energy landscape is defined whose gradient corresponds to the attention computation. Non-linear attention mechanisms offer a means to enhance the capabilities of transformer models for various sequence modeling tasks by improving the model&#8217;s understanding of complex relationships, learning of representations, and overall efficiency and performance. A rough analogy can be seen via cubic splines which offer a richer representation of non-linear data where a simpler linear model may be inadequate. This approach can be used for the introduction of non-linear heads in transformer based models such as BERT, [6], etc.<\/div>\n<p> \t<BR><br \/>\n <BR><\/BR><br \/>\n    Ahmed Farooq<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n<a href=\"https:\/\/arxiv.org\/abs\/2506.11043\">Go to original source<\/a><br \/>\n \t<BR><br \/>\n <BR><\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"<p>A Framework for Non-Linear Attention via Modern Hopfield Networks arXiv:2506.11043v1 Announce Type: new Abstract: In this work we propose an energy functional along the lines of Modern Hopfield Networks (MNH), the stationary points of which correspond to the attention due to Vaswani et al. [12], thus unifying both frameworks. The minima of this landscape form [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,113,1702,112],"tags":[960,496,1102],"class_list":["post-4626","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-lg","category-cs-ne","category-stat-ml","tag-attention","tag-linear","tag-non"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/4626"}],"collection":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/comments?post=4626"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/4626\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=4626"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=4626"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=4626"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}