--- title: Sequential Fitting: A Different Perspective on the... description: This research article introduces 'sequential fitting' as a new lens for understanding the spectral bias of neural networks — the well-known phenomenon where... canonical: https://daily.dev/posts/sequential-fitting-a-different-perspective-on-the-spectral-bias-of-neural-networks-k8od7p8bd twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Sequential Fitting: A Different Perspective on the Spectral Bias of Neural Networks | daily.dev og:description: This research article introduces 'sequential fitting' as a new lens for understanding the spectral bias of neural networks — the well-known phenomenon where... og:url: https://daily.dev/posts/sequential-fitting-a-different-perspective-on-the-spectral-bias-of-neural-networks-k8od7p8bd og:image: https://api.daily.dev/og/posts/k8od7p8bD.png og:image:alt: Sequential Fitting: A Different Perspective on the Spectral Bias of Neural Networks og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Sequential Fitting: A Different Perspective on the Spectral Bias of Neural Networks **[Towards Data Science](https://daily.dev/sources/tds)** · 15 min read · 0 upvotes · 0 comments ## Summary This research article introduces 'sequential fitting' as a new lens for understanding the spectral bias of neural networks — the well-known phenomenon where MLPs learn low-frequency components before high-frequency ones. The authors demonstrate that MLP networks with tanh activations fit high-frequency regression targets starting from domain boundaries and progressing inward, building one oscillation at a time. They also identify a 'boundary effect': two functions with nearly identical Fourier spectra can behave very differently as regression targets depending on how oscillations behave near domain boundaries. A basis function analysis reveals that these networks iteratively construct smoothed step functions rather than oscillatory bases, explaining the slow convergence on high-frequency targets. The phenomenon is demonstrated in both 1D and 2D regression settings, and contrasted with SIREN networks, which build oscillatory bases and avoid sequential fitting. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Teaching a Neural Network the Mandelbrot Set](https://daily.dev/posts/teaching-a-neural-network-the-mandelbrot-set-kfhxgggcg) · Towards Data Science · 1 upvotes · 0 comments - [Fourier Analysis Perspective on Quantum Neural Networks](https://daily.dev/posts/fourier-analysis-perspective-on-quantum-neural-networks-bkvn19bia) · Nature · 2 upvotes · 0 comments - [When Transformers Sing: Adapting SpectralKD for Text-Based Knowledge Distillation](https://daily.dev/posts/when-transformers-sing-adapting-spectralkd-for-text-based-knowledge-distillation-4x9ndjlyq) · Towards Data Science · 0 upvotes · 0 comments - [Recurrent Neural Networks \(RNNs\) From First Principles: The Complete Beginner Guide \(Part 1/2\)](https://daily.dev/posts/recurrent-neural-networks-rnns-from-first-principles-the-complete-beginner-guide-part-1-2--7plwxi8fp) · Medium · 0 upvotes · 0 comments --- Tags: [#neural-networks](https://daily.dev/tags/neural-networks) [View this post on daily.dev](https://daily.dev/posts/sequential-fitting-a-different-perspective-on-the-spectral-bias-of-neural-networks-k8od7p8bd) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Sequential Fitting: A Different Perspective on the Spectral Bias of Neural Networks","url":"https://daily.dev/posts/sequential-fitting-a-different-perspective-on-the-spectral-bias-of-neural-networks-k8od7p8bd","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/sequential-fitting-a-different-perspective-on-the-spectral-bias-of-neural-networks-k8od7p8bd"},"datePublished":"2026-06-08T14:03:43.585Z","dateModified":"2026-06-08T14:04:09.581Z","description":"This research article introduces 'sequential fitting' as a new lens for understanding the spectral bias of neural networks — the well-known phenomenon where...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c66cc402d3e1b0ec87c9c13f42e77966?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c66cc402d3e1b0ec87c9c13f42e77966?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Towards Data Science","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Towards Data Science","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/tds","url":"https://daily.dev/sources/tds"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/sequential-fitting-a-different-perspective-on-the-spectral-bias-of-neural-networks-k8od7p8bd","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"neural-networks","timeRequired":"PT15M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Towards Data Science","item":"https://daily.dev/sources/tds"},{"@type":"ListItem","position":3,"name":"Sequential Fitting: A Different Perspective on the Spectral Bias of Neural Networks"}]} ```