Physics-Informed Neural Networks in Medicine
Explore physics-informed neural networks' applications in medicine, focusing on innovative technologies combining data assimilation and machine learning.
Deep Distillation and Explainable Neural Networks (ENNs) - Lecture
Explore neurosymbolic architecture ENN, its bottom-up training, and deep distillation with Milo Lin. Gain insights into explainability, biological inspiration, and practical applications.
Certifying Trustworthy Deep Learning Systems
Explore techniques for certifying trustworthiness in deep learning systems with expert insights from Linyi Li, enhancing AI reliability and safety.
Self-Hosted AI Image Generation with InvokeAI
Explore self-hosted AI image generation with InvokeAI. Learn to create and edit stunning visuals, generate set pieces, and integrate them into your projects. Includes hardware recommendations and practical demonstrations.
Metric Space Magnitude and Generalization in Neural Networks
Exploring metric space magnitude in neural networks: new topological complexity measures for assessing generalization capabilities, with applications to transformers and deep graph networks.
Pioneering a Hybrid SSM Transformer Architecture - Jamba Foundation Model
Explore AI21 Labs' Jamba: a groundbreaking hybrid Transformer-Mamba MoE model with unparalleled throughput and a 256K context window, revolutionizing large language model development.
Temporal Difference Learning for Model Predictive Control - Research Presentation 3
Presentation on Temporal Difference Learning for Model Predictive Control, exploring innovative approaches in robotics and AI. Insights into recent papers and project developments by researcher Nicklas Hansen.
Boltzmann Machines - The Grandfather of Generative Models
Explore Boltzmann Machines, early generative models learning data probability distributions using stochastic rules and latent representations. Understand their goals, distribution, update rules, and evolution to Restricted Boltzmann Machines.
Understanding the Expressive Power of Transformers Through Formal Language Theory
Explore the intersection of formal language theory and machine learning, focusing on transformer expressiveness and recent developments in understanding their learning capabilities.
Descriptive Complexity for Distributed Computing and Neural Networks
Explore logics capturing distributed computing and neural network models, including graph neural networks. Dive into game-theoretic semantics and computational logic connections.
A Tutorial on Neurosymbolic Techniques
Explore neurosymbolic techniques for synthesizing models and systems, blending neural networks with symbolic reasoning to enhance AI capabilities.
Distributed Training and Gradient Compression - Part I - Lecture 13
Explore distributed training of neural networks, focusing on data parallelism and model parallelism techniques for efficient machine learning on resource-constrained devices.
Distributed Training and Gradient Compression - Part I - Lecture 13
Explore distributed training of neural networks, focusing on data parallelism and model parallelism techniques for efficient machine learning on resource-constrained devices.
Tensorflow and Deep Learning - Without a PhD
Explore deep machine learning with Tensorflow using Python. Learn to choose and optimize neural networks for various problems without advanced math prerequisites.
MIT 6.S191 - Recurrent Neural Networks
Comprehensive lecture on Recurrent Neural Networks, covering theory, implementation, and applications. Explores sequence modeling, LSTM, attention mechanisms, and practical examples in deep learning.
Intro to Deep Learning - ML Tech Talks
Comprehensive introduction to deep learning concepts, neural network architectures, and practical applications, featuring TensorFlow examples, code demos, and insights into representation learning and model interpretability.
Supermasks in Superposition - Paper Explained
Explore supermasks in neural networks for lifelong learning, tackling catastrophic forgetting and automatic task identification. Learn about mask superpositions, entropy minimization, and innovative extensions.
GShard- Scaling Giant Models with Conditional Computation and Automatic Sharding
Detailed explanation of Google's 600 billion parameter transformer for multilingual translation, focusing on scaling techniques, mixture-of-experts, and automatic sharding implementation on TPUs.
It's All About AI - Promises & Challenges in Computer Vision & NLP
Explore AI's potential through live demos in computer vision and NLP. Discover neural networks, deepfakes, chatbots, and AI-generated content. Gain insights into the promises and challenges of this transformative technology.
Introduction to Artificial Intelligence - The Complete Training Course
Comprehensive overview of AI fundamentals, applications, and impact on technology. Explores key concepts, current trends, and future potential of artificial intelligence in various industries.
A Connection between Probability, Physics and Neural Networks
Explore the intersection of probability, physics, and neural networks, focusing on constructing physics-consistent models using Gaussian processes and the central limit theorem.