Imagen de Portada

On the creation of narrow AI: hierarchy and nonlocality of neural network skills

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Michaud, Eric J., Parker-Sartori, Asher, Tegmark, Max
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The Quantization Model of Neural Scaling
por: Michaud, Eric J., et al.
Publicado: (2023)

Not All Language Model Features Are One-Dimensionally Linear
por: Engels, Joshua, et al.
Publicado: (2024)

Efficient Dictionary Learning with Switch Sparse Autoencoders
por: Mudide, Anish, et al.
Publicado: (2024)

Survival of the Fittest Representation: A Case Study with Modular Addition
por: Ding, Xiaoman Delores, et al.
Publicado: (2024)

Physics of Skill Learning
por: Liu, Ziming, et al.
Publicado: (2025)

Do Two AI Scientists Agree?
por: Fu, Xinghong, et al.
Publicado: (2025)

The Geometry of Concepts: Sparse Autoencoder Feature Structure
por: Li, Yuxiao, et al.
Publicado: (2024)

OptPDE: Discovering Novel Integrable Systems via AI-Human Collaboration
por: Kantamneni, Subhash, et al.
Publicado: (2024)

Opening the AI black box: program synthesis via mechanistic interpretability
por: Michaud, Eric J., et al.
Publicado: (2024)

Towards Understanding Distilled Reasoning Models: A Representational Approach
por: Baek, David D., et al.
Publicado: (2025)

Harmonic Loss Trains Interpretable AI Models
por: Baek, David D., et al.
Publicado: (2025)

When narrower is better: the narrow width limit of Bayesian parallel branching neural networks
por: Zhang, Zechen, et al.
Publicado: (2024)

Language Models Use Trigonometry to Do Addition
por: Kantamneni, Subhash, et al.
Publicado: (2025)

Language Models Represent Space and Time
por: Gurnee, Wes, et al.
Publicado: (2023)

High-dimensional learning of narrow neural networks
por: Cui, Hugo
Publicado: (2024)

Low-Rank Adapting Models for Sparse Autoencoders
por: Chen, Matthew, et al.
Publicado: (2025)

Decomposing The Dark Matter of Sparse Autoencoders
por: Engels, Joshua, et al.
Publicado: (2024)

Universal approximation with complex-valued deep narrow neural networks
por: Geuchen, Paul, et al.
Publicado: (2023)

A Neural Scaling Law from Lottery Ticket Ensembling
por: Liu, Ziming, et al.
Publicado: (2023)

Improved weight initialization for deep and narrow feedforward neural network
por: Lee, Hyunwoo, et al.
Publicado: (2023)

GenEFT: Understanding Statics and Dynamics of Model Generalization via Effective Theory
por: Baek, David D., et al.
Publicado: (2024)

Investigating Representation Universality: Case Study on Genealogical Representations
por: Baek, David D., et al.
Publicado: (2024)

Generating adversarial inputs for a graph neural network model of AC power flow
por: Parker, Robert
Publicado: (2026)

Luck, skill, and depth of competition in games and social hierarchies
por: Jerdee, Maximilian, et al.
Publicado: (2023)

How Do Transformers "Do" Physics? Investigating the Simple Harmonic Oscillator
por: Kantamneni, Subhash, et al.
Publicado: (2024)

Association-sensory spatiotemporal hierarchy and functional gradient-regularised recurrent neural network with implications for schizophrenia
por: Abulikemu, Subati, et al.
Publicado: (2025)

An in-depth look at approximation via deep and narrow neural networks
por: Dommel, Joris, et al.
Publicado: (2025)

A Resource Model For Neural Scaling Law
por: Song, Jinyeop, et al.
Publicado: (2024)

Understanding sparse autoencoder scaling in the presence of feature manifolds
por: Michaud, Eric J., et al.
Publicado: (2025)

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
por: Kantamneni, Subhash, et al.
Publicado: (2025)

Scaling Laws For Scalable Oversight
por: Engels, Joshua, et al.
Publicado: (2025)

The Remarkable Robustness of LLMs: Stages of Inference?
por: Lad, Vedang, et al.
Publicado: (2024)

Neural Thermodynamic Laws for Large Language Model Training
por: Liu, Ziming, et al.
Publicado: (2025)

Formulations and scalability of neural network surrogates in nonlinear optimization problems
por: Parker, Robert B., et al.
Publicado: (2024)

Scaling transformer neural networks for skillful and reliable medium-range weather forecasting
por: Nguyen, Tung, et al.
Publicado: (2023)

A Case for Library-Level k-Means Binning in Histogram Gradient-Boosted Trees
por: Labovich, Asher
Publicado: (2025)

Foundation Models for AI-Enabled Biological Design
por: Moldwin, Asher, et al.
Publicado: (2025)

Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models
por: Testolin, Alberto
Publicado: (2023)

Fixed points of nonnegative neural networks
por: Piotrowski, Tomasz J., et al.
Publicado: (2021)

The Artificial Intelligence Ontology: LLM-assisted construction of AI concept hierarchies
por: Joachimiak, Marcin P., et al.
Publicado: (2024)