What Is ChatGPT Doing and Why Does It Work?
Explore the inner workings and underlying principles of ChatGPT, delving into its functionality and effectiveness in natural language processing and generation.
Exploring Molecular Space and Active Learning in Drug Discovery
Explore molecular space and active learning techniques for drug discovery with AI pioneer Yoshua Bengio's insights from the 2024 ML Summer School at Mila.
Learning ML Interatomic Potentials - Day 2
Explore ML interatomic potentials for drug discovery with expert Gianni De Fabritiis. Gain insights into advanced techniques and applications in computational chemistry.
Geometric Deep Learning for Protein Understanding
Explore geometric deep learning techniques for protein analysis and understanding, focusing on advanced computational methods in molecular biology.
Approximately Piecewise E(3) Equivariant Point Networks
Explore APEN: a framework for approximate piecewise-E(3) equivariant point networks, improving generalization in part-based symmetry tasks like room scene analysis and human motion recognition.
Accelerating Simulations of Particle Systems Using Machine Learning
Explore machine learning techniques for accelerating particle system simulations using transformer-based architectures and Mathematica.
New Additions to Wolfram Neural Net Repository - Overview and Applications
Explore the latest pre-trained models in Wolfram's Neural Net Repository, covering NLP, computer vision, and audio analysis, with insights on their applications and integration.
AI-Based Environmentally Sustainable Cardiovascular Disease Diagnostic
Explore an LSTM-based diagnostic tool for CVDs, reducing misdiagnoses and medical waste while achieving high accuracy in disease detection.
What's New in Wolfram Image and Audio Processing - Recent Developments and Applications
Explore cutting-edge AI advancements in image and signal processing, including segmentation, OCR, and speech technologies, with powerful neural network applications.
Analyzing GPT-2's Brain Development
Explore GPT-2's inner workings through token manipulation, node analysis, and temperature adjustments to gain insights into its structure and functioning.
Evaluating Complexity for Neural Nets in Learning Math Functions
Explore neural net complexity's impact on learning math functions through criteria analysis and optimization techniques.
XAI: A Model to Explain StyleGANs
Explore an innovative explanation model for StyleGANs using active shape and appearance models in this computational essay.
Machine Learning for Real-Time Hydrate Risk in LNG Facilities
Explore advanced neural networks in Wolfram Language for real-time hydrate risk monitoring in LNG facilities using simulation-based data.
What's Really Going On in Machine Learning? Some Minimal Models - Stephen Wolfram Reading
Explore Stephen Wolfram's insights on machine learning through minimal models, covering neural nets, discrete rule arrays, and optimization processes. Gain a deeper understanding of ML fundamentals and their implications.
Score Matching via Differentiable Physics
Explore score matching via differentiable physics for inverse problems. Learn about combining physics operators with stochastic differential equations to generate plausible trajectories towards given end states.
Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions
Explore neural set function extensions for integrating discrete functions into neural networks, focusing on continuous domain extensions and high-dimensional representations for combinatorial optimization.
MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
Explore higher-order equivariant message passing neural networks for fast, accurate force fields in computational chemistry. Learn about MACE's innovative approach using four-body messages to enhance efficiency and accuracy.
Introducing Bioptic - Machine Learning for Drug Discovery
Explore Bioptic's architecture, training, and scaling for machine learning in drug discovery with Vlad Vinograv.
Generalization in Diffusion Models from Geometry-Adaptive Harmonic Representation
Explore generalization in diffusion models through geometry-adaptive harmonic representation. Analyze denoising DNNs, score functions, and inductive biases to understand high-dimensional density learning and optimal basis adaptation.
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
Explore advanced diffusion models with Consistency Trajectory Models, improving sample quality and efficiency in AI-driven image generation. Learn novel sampling techniques and state-of-the-art results.
Pre-training via Denoising for Molecular Property Prediction
Explore pre-training via denoising for molecular property prediction, learning force fields from equilibrium structures to improve generalization and achieve state-of-the-art results on QM9 dataset.