gladia-research-group / explanatory-learning
This is the official repository for "Explanatory Learning: Beyond Empiricism in Neural Networks".
☆14Updated 2 years ago
Alternatives and similar repositories for explanatory-learning:
Users that are interested in explanatory-learning are comparing it to the libraries listed below
- A Python package for analyzing and transforming neural latent spaces.☆44Updated 3 months ago
- How to Turn Your Knowledge Graph Embeddings into Generative Models☆50Updated 7 months ago
- Mechanistic Interpretability for Transformer Models☆49Updated 2 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- Personal implementation of ASIF by Antonio Norelli☆25Updated 9 months ago
- Relative representations can be leveraged to enable solving tasks regarding "latent communication": from zero-shot model stitching to lat…☆56Updated last year
- The Energy Transformer block, in JAX☆56Updated last year
- ☆26Updated last year
- ☆61Updated 2 years ago
- ☆84Updated 2 weeks ago
- ☆34Updated 2 months ago
- ☆58Updated this week
- ☆53Updated last year
- The Recognizing, Exploring, and Articulating Limitations in Machine Learning research tool (REAL ML) is a set of guided activities to hel…☆51Updated 2 years ago
- Probabilistic programming with HuggingFace language models☆100Updated last week
- Stochastic Automatic Differentiation library for PyTorch.☆197Updated 6 months ago
- Representation Learning on Topological Domains☆79Updated this week
- Code associated to papers on superposition (in ML interpretability)☆28Updated 2 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated last month
- Deep relational learning through differentiable logic programming.☆102Updated 7 months ago
- PyTorch-based library for various kinds of representational-similarity analysis☆23Updated 8 months ago
- Neural Networks and the Chomsky Hierarchy☆204Updated 10 months ago
- Understanding how features learned by neural networks evolve throughout training☆33Updated 4 months ago
- Fine-grained, dynamic control of neural network topology in JAX.☆21Updated last year
- Implementation of "SALSA-CLRS: A Sparse and Scalable Benchmark for Algorithmic Reasoning". SALSA-CLRS is an extension to the original clr…☆16Updated last year
- ☆59Updated 2 years ago
- ☆16Updated 10 months ago
- Language-annotated Abstraction and Reasoning Corpus☆82Updated last year
- ☆18Updated last year
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆165Updated last year