Copertina

How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cagnetta, Francesco, Petrini, Leonardo, Tomasini, Umberto M., Favero, Alessandro, Wyart, Matthieu
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model
di: Tomasini, Umberto, et al.
Pubblicazione: (2024)

A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data
di: Sclocchi, Antonio, et al.
Pubblicazione: (2024)

How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
di: Favero, Alessandro, et al.
Pubblicazione: (2025)

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures
di: Cagnetta, Francesco, et al.
Pubblicazione: (2025)

Towards a theory of how the structure of language is acquired by deep neural networks
di: Cagnetta, Francesco, et al.
Pubblicazione: (2024)

Deep networks learn to parse uniform-depth context-free languages from local statistics
di: Parley, Jack T., et al.
Pubblicazione: (2026)

Learning curves theory for hierarchically compositional data with power-law distributed features
di: Cagnetta, Francesco, et al.
Pubblicazione: (2025)

Deriving Neural Scaling Laws from the statistics of natural language
di: Cagnetta, Francesco, et al.
Pubblicazione: (2026)

Deep Neural Network Models Trained With A Fixed Random Classifier Transfer Better Across Domains
di: Ali, Hafiz Tiomoko, et al.
Pubblicazione: (2024)

Compositional Curvature Bounds for Deep Neural Networks
di: Entesari, Taha, et al.
Pubblicazione: (2024)

Hier-COS: Making Deep Features Hierarchy-aware via Composition of Orthogonal Subspaces
di: Sani, Depanshu, et al.
Pubblicazione: (2025)

An Explainable Fast Deep Neural Network for Emotion Recognition
di: Di Luzio, Francesco, et al.
Pubblicazione: (2024)

Adaptive Data Dropout: Towards Self-Regulated Learning in Deep Neural Networks
di: Gahir, Amar, et al.
Pubblicazione: (2026)

Efficient Adaptation of Deep Neural Networks for Semantic Segmentation in Space Applications
di: Olivi, Leonardo, et al.
Pubblicazione: (2025)

Incremental Online Learning of Randomized Neural Network with Forward Regularization
di: Wang, Junda, et al.
Pubblicazione: (2024)

Recursive Neural Programs: Variational Learning of Image Grammars and Part-Whole Hierarchies
di: Fisher, Ares, et al.
Pubblicazione: (2022)

Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models
di: Favero, Alessandro, et al.
Pubblicazione: (2025)

Backdoor Unlearning by Linear Task Decomposition
di: Abdelraheem, Amel, et al.
Pubblicazione: (2025)

FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models
di: Caligiuri, Matteo, et al.
Pubblicazione: (2025)

Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks
di: Yamaguchi, Shin'ya, et al.
Pubblicazione: (2024)

PHyCLIP: $\ell_1$-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning
di: Yoshikawa, Daiki, et al.
Pubblicazione: (2025)

Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones
di: Risso, Matteo, et al.
Pubblicazione: (2024)

Are Face Embeddings Compatible Across Deep Neural Network Models?
di: Rubab, Fizza, et al.
Pubblicazione: (2026)

Quantized and Interpretable Learning Scheme for Deep Neural Networks in Classification Task
di: Maleki, Alireza, et al.
Pubblicazione: (2024)

How to Train Your Metamorphic Deep Neural Network
di: Sommariva, Thomas, et al.
Pubblicazione: (2025)

Visual Concept Networks: A Graph-Based Approach to Detecting Anomalous Data in Deep Neural Networks
di: Ganguly, Debargha, et al.
Pubblicazione: (2024)

LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging
di: Wang, Ke, et al.
Pubblicazione: (2024)

Dual Precision Deep Neural Network
di: Park, Jae Hyun, et al.
Pubblicazione: (2020)

Classification of Building Information Model (BIM) Structures with Deep Learning
di: Lomio, Francesco, et al.
Pubblicazione: (2018)

Neural Redshift: Random Networks are not Random Functions
di: Teney, Damien, et al.
Pubblicazione: (2024)

How Weight Resampling and Optimizers Shape the Dynamics of Continual Learning and Forgetting in Neural Networks
di: Frati, Lapo, et al.
Pubblicazione: (2025)

Hierarchy-Guided Multimodal Representation Learning for Taxonomic Inference
di: Ahmed, Sk Miraj, et al.
Pubblicazione: (2026)

Learn from your own latents and not from tokens: A sample-complexity theory
di: Korchinski, Daniel J., et al.
Pubblicazione: (2026)

Lipschitz Constant Meets Condition Number: Learning Robust and Compact Deep Neural Networks
di: Feng, Yangqi, et al.
Pubblicazione: (2025)

DQA: An Efficient Method for Deep Quantization of Deep Neural Network Activations
di: Hu, Wenhao, et al.
Pubblicazione: (2024)

Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data
di: Li, Yuxuan, et al.
Pubblicazione: (2024)

How Deep is Your Art: An Experimental Study on the Limits of Artistic Understanding in a Single-Task, Single-Modality Neural Network
di: Zahedi, Mahan Agha, et al.
Pubblicazione: (2022)

Calibrating Deep Neural Network using Euclidean Distance
di: Liang, Wenhao, et al.
Pubblicazione: (2024)

Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection
di: Feifel, Patrick, et al.
Pubblicazione: (2025)

HEIR: Learning Graph-Based Motion Hierarchies
di: Zheng, Cheng, et al.
Pubblicazione: (2025)