Stanford Seminar 2022 - Self Attention and Non-Parametric Transformers
Explore self-attention and Non-Parametric Transformers with PhD students discussing Transformer origins, intuitions, and recent advancements in neural network architecture.
Stanford Seminar - Mixture of Experts Paradigm and the Switch Transformer
Explore the Mixture of Experts paradigm and Switch Transformer, revolutionizing deep learning with sparsely-activated models for improved efficiency and performance in language processing tasks.
Stanford Seminar - Decision Transformer: Reinforcement Learning via Sequence Modeling
Innovative approach to reinforcement learning using sequence modeling and Transformer architecture, offering simplicity and scalability while matching or exceeding state-of-the-art performance in various tasks.
Stanford Seminar - Dataflow for Convergence of AI and HPC - GroqChip
Explore dataflow history, AI-HPC convergence, and Groq's tensor streaming processor architecture. Learn about stream programming, deterministic execution, and distributed scale-out systems for efficient deep learning computations.
Petascale Deep Learning on a Single Chip
Innovative deep learning processor architecture for improved efficiency and performance, featuring strategies to reduce data movement and enhance scalability for next-generation models.
NVIDIA GPU Computing - A Journey from PC Gaming to Deep Learning
Explore NVIDIA GPU's evolution from gaming to deep learning, covering key architectures and applications in supercomputing, data centers, and autonomous vehicles.
Information Theory of Deep Learning - Naftali Tishby
Explores the connection between deep learning and information theory, offering new insights into neural network design, generalization, and optimization through an information bottleneck framework.
Deep Learning - Adversarial Attacks and GANs - Lecture 4
Explore adversarial attacks and Generative Adversarial Networks (GANs) in deep learning. Learn from Stanford experts about these advanced techniques and their applications in AI.
Deep Learning Full-Cycle Projects - Lecture 3
Comprehensive exploration of full-cycle deep learning projects, covering project selection, visualization, and problem-solving techniques for voice-activated devices and network challenges.
Deep Learning Intuition - Lecture 2
Explore deep learning intuition with Stanford experts, covering logistic regression, face verification, neural architectures, and advanced applications in computer vision and image processing.
Deep Learning - Class Introduction and Logistics - Lecture 1
Comprehensive introduction to deep learning, covering key concepts, tools, and applications. Explores course goals, structure, and practical assignments for hands-on experience in AI and machine learning.
Deep Learning in the Age of Zen, Vega, and Beyond
Explore deep learning challenges and solutions using AMD's Zen and Vega platforms, focusing on high-performance computing for training and inference in various applications.
MRI as a Low-Cost High-Value Imaging Modality - Spring 2020
Explore advancements in MRI technology, focusing on improving cost-effectiveness, efficiency, and diagnostic capabilities for various medical conditions, particularly in orthopedics and cancer screening.
How I Learned to Stop Worrying and Love the Transformer - Stanford CS25 Lecture
Explore the Transformer's evolution and future directions with Ashish Vaswani, co-author of "Attention is All You Need". Gain insights into motivations, developments, and promising research areas in AI and NLP.
Shaping the Future of AI from the History of Transformer Architectures - Stanford CS25
Explore the evolution of Transformer architectures and AI development with OpenAI researcher Hyung Won Chung, focusing on historical motivations and future projections in the field.
Deep Generative Models - Autoregressive Models - Lecture 3
Explore autoregressive models in deep learning, focusing on their architecture, training, and applications in generating sequential data like text and images.
Deep Generative Models - Lecture 5: Variational Autoencoders
Explore Variational Autoencoders (VAEs) in deep generative modeling, covering theoretical foundations and practical applications in this comprehensive Stanford lecture.
Deep Generative Models - Diffusion Models for Discrete Data - Lecture 18
Explore diffusion models for discrete data in this Stanford lecture, covering advanced techniques in deep generative modeling for AI applications.
Deep Generative Models - Normalizing Flows - Lecture 9
Explore normalizing flows in deep generative models, focusing on their principles, applications, and recent advancements in this Stanford lecture by Prof. Stefano Ermon.
Deep Generative Models - Lecture 6: Variational Autoencoders
Explore Variational Autoencoders (VAEs) in deep generative modeling, covering theoretical foundations and practical applications in this Stanford lecture by Prof. Stefano Ermon.
Evaluation of Generative Models - Stanford CS236 Deep Generative Models Lecture 15
Explore evaluation methods for deep generative models, including metrics and techniques to assess model performance, quality, and effectiveness in various applications.