Cover Image

Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bencomo, Gianluca, Gupta, Max, Marinescu, Ioana, McCoy, R. Thomas, Griffiths, Thomas L.
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Distilling Symbolic Priors for Concept Learning into Neural Networks
by: Marinescu, Ioana, et al.
Published: (2024)

Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning
by: Prabhakar, Akshara, et al.
Published: (2024)

Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear
by: McCoy, R. Thomas
Published: (2026)

Identifying and Mitigating the Influence of the Prior Distribution in Large Language Models
by: Zhang, Liyi, et al.
Published: (2025)

Collocational bootstrapping: A hypothesis about the learning of subject-verb agreement in humans and neural networks
by: Hobbs, Claire, et al.
Published: (2026)

Convolutional Neural Networks Can (Meta-)Learn the Same-Different Relation
by: Gupta, Max, et al.
Published: (2025)

Whither symbols in the era of advanced neural networks?
by: Griffiths, Thomas L., et al.
Published: (2025)

When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1
by: McCoy, R. Thomas, et al.
Published: (2024)

Human and Automatic Interpretation of Romanian Noun Compounds
by: Marinescu, Ioana, et al.
Published: (2024)

Compositional Sparsity as an Inductive Bias for Neural Architecture Design
by: Lin, Hongyu, et al.
Published: (2026)

Minimization of Boolean Complexity in In-Context Concept Learning
by: Wang, Leroy Z., et al.
Published: (2024)

What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions
by: Zhang, Liyi, et al.
Published: (2024)

A Relational Inductive Bias for Dimensional Abstraction in Neural Networks
by: Campbell, Declan, et al.
Published: (2024)

GPU-Accelerated ANNS: Quantized for Speed, Built for Change
by: McCoy, Hunter, et al.
Published: (2026)

Learning Human-Aligned Representations with Contrastive Learning and Generative Similarity
by: Marjieh, Raja, et al.
Published: (2024)

Dominion: A New Frontier for AI Research
by: Halawi, Danny, et al.
Published: (2024)

Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers
by: Sankaran, Shyam, et al.
Published: (2026)

GRR-CoCa: Leveraging LLM Mechanisms in Multimodal Model Architectures
by: Patock, Jake R., et al.
Published: (2025)

Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
by: Jiralerspong, Thomas, et al.
Published: (2025)

Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis
by: Lee, Hyunwoo, et al.
Published: (2024)

Cognitive Architectures for Language Agents
by: Sumers, Theodore R., et al.
Published: (2023)

Human-Like Geometric Abstraction in Large Pre-trained Neural Networks
by: Campbell, Declan, et al.
Published: (2024)

Levels of Analysis for Large Language Models
by: Ku, Alexander Y., et al.
Published: (2025)

Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations
by: Zhu, Jian-Qiao, et al.
Published: (2025)

Understanding Task Representations in Neural Networks via Bayesian Ablation
by: Nam, Andrew, et al.
Published: (2025)

Functorial Neural Architectures from Higher Inductive Types
by: Sargsyan, Karen
Published: (2026)

The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology
by: Yıldırım, Alper
Published: (2026)

Toward Efficient Exploration by Large Language Model Agents
by: Arumugam, Dilip, et al.
Published: (2025)

The Relational Bottleneck as an Inductive Bias for Efficient Abstraction
by: Webb, Taylor W., et al.
Published: (2023)

Uncovering the Role of Initial Saliency in U-Shaped Attention Bias: Scaling Initial Token Weight for Enhanced Long-Text Processing
by: Qiang, Zewen, et al.
Published: (2025)

Understanding Inequality of LLM Fact-Checking over Geographic Regions with Agent and Retrieval models
by: Coelho, Bruno, et al.
Published: (2025)

Global-Liar: Factuality of LLMs over Time and Geographic Regions
by: Mirza, Shujaat, et al.
Published: (2024)

Disentangling Granularity: An Implicit Inductive Bias in Factorized VAEs
by: Chen, Zihao, et al.
Published: (2025)

Soft Geometric Inductive Bias for Object Centric Dynamics
by: Linander, Hampus, et al.
Published: (2025)

Graph Alignment Topology as an Inductive Bias for Grounding Detection
by: Landes, Paul, et al.
Published: (2026)

On the Inductive Bias of Stacking Towards Improving Reasoning
by: Saunshi, Nikunj, et al.
Published: (2024)

Spectral Architecture Search for Neural Network Models
by: Peri, Gianluca, et al.
Published: (2025)

On Time-Indexing as Inductive Bias in Deep RL for Sequential Manipulation Tasks
by: Qureshi, M. Nomaan, et al.
Published: (2024)

The Manuscript as Question: Teaching Primary Sources in the Archives--The China Missions Project
by: McCoy, Michelle
Published: (2010)

Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges
by: Kosman, Eitan, et al.
Published: (2026)