GitHub topics: inductive-biases

Repositories

sayakpaul/deit-tf

Includes PyTorch -> Keras model porting code for DeiT models with fine-tuning and inference notebooks.

Language: Jupyter Notebook - Size: 40.4 MB - Last synced at: 7 days ago - Pushed at: about 3 years ago - Stars: 41 - Forks: 7

rfeinman/learning-to-learn

Code for "Learning Inductive Biases with Simple Neural Networks" (Feinman & Lake, 2018).

Language: Python - Size: 472 MB - Last synced at: about 1 month ago - Pushed at: over 6 years ago - Stars: 22 - Forks: 6

christos42/inductive_bias_IE

An Information Extraction Study: Take In Mind the Tokenization! (official repository of the paper)

Language: Shell - Size: 1.17 MB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 6 - Forks: 1

shikhartuli/cnn_txf_bias

[CogSci'21] Study of human inductive biases in CNNs and Transformers.

Language: Jupyter Notebook - Size: 214 MB - Last synced at: 5 months ago - Pushed at: almost 4 years ago - Stars: 43 - Forks: 3

sayakpaul/vision-transformers-tf

A non-exhaustive collection of vision transformer models implemented in TensorFlow.

Size: 6.84 KB - Last synced at: about 1 month ago - Pushed at: over 2 years ago - Stars: 10 - Forks: 1

zdxdsw/inductive_counting_with_LMs

This work provides extensive empirical results on training LMs to count. We find that while traditional RNNs trivially achieve inductive counting, Transformers have to rely on positional embeddings to count out-of-domain. Modern RNNs (e.g. rwkv, mamba) also largely underperform traditional RNNs in generalizing counting inductively.

Language: Jupyter Notebook - Size: 653 MB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 2 - Forks: 0

cambridgeltl/ECNMT

Emergent Communication Pretraining for Few-Shot Machine Translation

Language: Python - Size: 2.8 MB - Last synced at: 12 months ago - Pushed at: over 4 years ago - Stars: 13 - Forks: 3

dalab/matrix-manifolds

Source code for the "Computationally Tractable Riemannian Manifolds for Graph Embeddings" paper

Language: Python - Size: 23 MB - Last synced at: about 1 year ago - Pushed at: almost 5 years ago - Stars: 34 - Forks: 2

NeurAI-Lab/InBiaseD

This is the official code for CoLLAs 2022 paper, "InBiaseD: Inductive Bias Distillation to Improve Generalization and Robustness through Shape-awareness"

Language: Python - Size: 650 KB - Last synced at: over 1 year ago - Pushed at: almost 3 years ago - Stars: 4 - Forks: 0

mahsa91/GKD-MICCAI2021

Implementation code of GKD: Semi-supervised Graph Knowledge Distillation for Graph-Independent Inference accepted by Medical Image Computing and Computer Assisted Interventions (MICCAI 2021)

Language: Python - Size: 1.63 MB - Last synced at: over 1 year ago - Pushed at: almost 3 years ago - Stars: 2 - Forks: 0