Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching

Deep Learning Demystified | Will Ramey Nvidia GTC

Applied AI | Foundation Models of Scientific Knowledge for Chemistry

Dataset | Tutorial on Theory and Practice of Efficient and Accurate Dataset Construction | NeurIPS

Lifelong Learning | Tutorial on Lifelong Learning Approaches - Part 2 | NeurIPS

Lifelong Learning | Tutorial on Lifelong Learning Machines (Panel Talk) | NeurIPS

Yoshua Bengio sharing on his Deep Learning Journey

Role play with Large Language Model #LLM | Thomas Wolf

150X FASTER DataFrame Processing !!!#deeplearning #pandas #df #nvidia #rapids #science #ai

Deep Learning | A Deep Learning Journey | Yoshua Bengio | NeurIPS

Applied AI | Insights from NVIDIA Research | Bill Dally

CV | Raytracing for Deep Neural Networks Training

NLP | Faster Transformer

3D | Deep Learning for 3D Vision

Data Visualization | High-Performance, Remote Scientific Visualization in Jupyter Notebooks

Tabular Data | Google TabNet: Interpretable Tabular Data Learning | AAAI

Meta-Learning | AAAI Tutorial

Deep Learning | Learning with Small Data

Applied AI | Drug Discovery

Deep Learning | Deep Randomized Neural Network

Time Series | Informer - Beyond Efficient Transformer for Long Sequence Time-Series Forecasting

Self-Supervised Learning | Curiosity Driven Exploration by Self-Supervised Prediction

Self-Supervised Learning | Self-supervision for Learning from the Bottom Up by Alexei A. Efros

Representation Learning | Compression with Implicit Neural Representations

General AI | Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator