Reinforcement learning: Fast and slow - Matthew Botvinick

Автор: Stanford

Загружено: 2018-11-16

Просмотров: 9809

Описание:

Matthew Botvinick’s work straddles the boundaries between cognitive psychology, computational and experimental neuroscience and artificial intelligence. In this talk Dr. Botvinick will review recent developments in deep reinforcement learning (RL), showing how deep RL can proceed rapidly, and also have interesting potential implications for our understanding of human learning and neural function.

Reinforcement learning: Fast and slow - Matthew Botvinick

Доступные форматы для скачивания:

Скачать видео mp4

Информация по загрузке:

Скачать аудио mp3

Похожие видео

Обучение с подкреплением, быстрое и медленное

Обучение с подкреплением, быстрое и медленное

The Prefrontal Cortex as a Meta-Reinforcement Learning System

The Prefrontal Cortex as a Meta-Reinforcement Learning System

Modern AI and the state of interdisciplinary exchange with neuroscience - Greg Corrado

Modern AI and the state of interdisciplinary exchange with neuroscience - Greg Corrado

Matthew Botvinick - AI as a Window on Human Intelligence (December 7, 2022)

Matthew Botvinick - AI as a Window on Human Intelligence (December 7, 2022)

LLM и GPT - как работают большие языковые модели? Визуальное введение в трансформеры

LLM и GPT - как работают большие языковые модели? Визуальное введение в трансформеры

David Silver: AlphaGo, AlphaZero, and Deep Reinforcement Learning | Lex Fridman Podcast #86

David Silver: AlphaGo, AlphaZero, and Deep Reinforcement Learning | Lex Fridman Podcast #86

System Design Concepts Course and Interview Prep

System Design Concepts Course and Interview Prep

Matt Botvinick - Holy Grail Questions at the Intersection of Neuroscience and AI

Matt Botvinick - Holy Grail Questions at the Intersection of Neuroscience and AI

Policy Gradient Theorem Explained - Reinforcement Learning

Policy Gradient Theorem Explained - Reinforcement Learning

Stanford CS230 | Autumn 2025 | Lecture 9: Career Advice in AI

Stanford CS230 | Autumn 2025 | Lecture 9: Career Advice in AI

Принцип свободной энергии — Карл Фристон

Принцип свободной энергии — Карл Фристон

Неожиданная правда о 4 миллиардах лет эволюции [Veritasium]

Неожиданная правда о 4 миллиардах лет эволюции [Veritasium]

Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs | Lex Fridman Podcast #11

Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs | Lex Fridman Podcast #11

A History of Reinforcement Learning - Prof. A.G. Barto

A History of Reinforcement Learning - Prof. A.G. Barto

Обучение с подкреплением с нуля

Обучение с подкреплением с нуля

Matt Botvinick-Deep reinforcement learning and its neuroscientific implications

Matt Botvinick-Deep reinforcement learning and its neuroscientific implications

Reinforcement Learning

Reinforcement Learning

Meta Learning Can Spontaneously Happen in Recurrent Neural Networks (Matt Botvinick) | Lex Fridman

Meta Learning Can Spontaneously Happen in Recurrent Neural Networks (Matt Botvinick) | Lex Fridman

Градиентный спуск, как обучаются нейросети | Глава 2, Глубинное обучение

Градиентный спуск, как обучаются нейросети | Глава 2, Глубинное обучение

Matt Botvinick: Neuroscience, Psychology, and AI at DeepMind | Lex Fridman Podcast #106

Matt Botvinick: Neuroscience, Psychology, and AI at DeepMind | Lex Fridman Podcast #106