UC Berkeley EECS Courses

Quantum Systems Engineering - From Research to Development

Delve into quantum computing systems engineering with pioneering physicist John Martinis as he explores the transition from research to practical quantum computer development and implementation challenges.

• YouTube
• 59 minutes
• On-Demand
• Free Video

Mapping and Mending Dexterous Movement Control with Neurotechnology

Explore the neural mechanisms behind dexterous movement and discover cutting-edge neurotechnology approaches for restoring motor function in patients with movement disorders through innovative brain-machine interfaces.

• YouTube
• 1 hour 10 minutes
• On-Demand
• Free Video

The Computer in the Sky - Blockchain Protocols and Digital Ownership

Explore blockchain technology and its vision of a shared, open-access computing platform through insights on distributed computing, cryptography, and algorithmic game theory from a leading computer scientist.

• YouTube
• 1 hour 8 minutes
• On-Demand
• Free Video

Disruptive Innovation and Collaboration to Sustain the AI Revolution

Explore the future of AI and microelectronics with insights from UC Berkeley's Dean of Engineering on overcoming technological challenges through innovation and collaborative approaches to sustain AI advancement.

• YouTube
• 1 hour 15 minutes
• On-Demand
• Free Video

New Pathways for Energy Efficient Computing Hardware

Explore groundbreaking approaches to energy-efficient computing hardware, focusing on physics-based solutions and functional materials that enhance CMOS technology for improved logic and memory performance.

• YouTube
• 1 hour 3 minutes
• On-Demand
• Free Video

Making Autonomous Systems Safe - One in a Billion Failure Rate

Explore the critical challenges and methodologies for ensuring autonomous systems meet billion-to-one safety standards through model-based simulations, testing protocols, and formal specifications.

• YouTube
• 1 hour 12 minutes
• On-Demand
• Free Video

Mixed-Autonomy Traffic at Scale: The MegaVanderTest Self-Driving Vehicle Study

Discover groundbreaking research on self-driving vehicle traffic control through the MegaVanderTest experiment, exploring optimal control algorithms, deep reinforcement learning, and practical implementation challenges.

• YouTube
• 1 hour 8 minutes
• On-Demand
• Free Video

Using AI to Understand AI

Explore cutting-edge approaches to understanding AI systems, focusing on interpretability, analysis methods, and the latest research in AI comprehension with Berkeley's expert guidance.

• YouTube
• 1 hour 7 minutes
• On-Demand
• Free Video

AI Safety Primer and Representation Engineering

Explore essential AI safety concepts and representation engineering techniques with insights from a leading expert in AI safety and computer science research.

• YouTube
• 1 hour 18 minutes
• On-Demand
• Free Video

Models Within Models - How Do LLMs Represent the World?

Explore how Large Language Models internally represent and process information, examining their complex architectures and mechanisms for understanding the world.

• YouTube
• 1 hour 15 minutes
• On-Demand
• Free Video

Benchmarks and Evaluations - Safety versus Capabilities in Machine Ethics

Explore critical aspects of AI evaluation, safety considerations, and ethical frameworks in large language models through expert insights on benchmarking and capability assessment.

• YouTube
• 1 hour 19 minutes
• On-Demand
• Free Video

The Security of Large Language Models

Explore critical security challenges and vulnerabilities in Large Language Models with insights from Google DeepMind's research scientist on threat assessment and protection strategies.

• YouTube
• 1 hour 17 minutes
• On-Demand
• Free Video

Inside-Out Interpretability: Training Dynamics in Multi-Layer Transformer

Delve into transformer model training dynamics and interpretability, exploring multi-layer architectures and their behavior through advanced analysis techniques with Meta AI researcher Yuandong Tian.

• YouTube
• 1 hour 7 minutes
• On-Demand
• Free Video

Memorization in Language Models - Understanding and Analysis

Delve into the complex phenomenon of memorization in language models, exploring key research findings and implications for AI development from UC Berkeley's expert analysis.

• YouTube
• 1 hour 6 minutes
• On-Demand
• Free Video

Interpretability and Model Editing in Large Language Models

Explore cutting-edge techniques in AI model interpretability and editing methods, focusing on understanding and modifying neural network behaviors with expert insights from Prof. David Bau.

• YouTube
• 1 hour 24 minutes
• On-Demand
• Free Video