Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Discovering Composable Modules in Meta-learning

Description

This lecture explores the concept of discovering composable modules in meta-learning, focusing on the development of a flexible framework for machine learning. The instructor discusses the unprecedented success in AI, efficient learning, broad generalization, and robustness inspired by human learning. Various techniques such as modular meta-learning, model agnostic meta-learning, and Noether Networks are presented, showcasing the advantages and disadvantages of tailoring models during search. The lecture delves into the application of Noether Networks in reducing object morphing artifacts and improving the efficiency of reinforcement learning. Additionally, the importance of encoding inductive biases and the role of symmetries in discovering useful inductive biases are highlighted.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Official source

Related concepts (32)

Machine learning

Machine learning (ML) is an umbrella term for solving problems for which development of algorithms by human programmers would be cost-prohibitive, and instead the problems are solved by helping machines 'discover' their 'own' algorithms, without needing to be explicitly told what to do by any human-developed algorithms. Recently, generative artificial neural networks have been able to surpass results of many previous approaches.

Share (finance)

In financial markets, a share (sometimes referred to as stock) is a unit of equity ownership in the capital stock of a corporation, and can refer to units of mutual funds, limited partnerships, and real estate investment trusts. Share capital refers to all of the shares of an enterprise. The owner of shares in a company is a shareholder (or stockholder) of the corporation. A share is an indivisible unit of capital, expressing the ownership relationship between the company and the shareholder.

Share price

A share price is the price of a single share of a number of saleable equity shares of a company. In layman's terms, the stock price is the highest amount someone is willing to pay for the stock, or the lowest amount that it can be bought for. In economics and financial theory, analysts use random walk techniques to model behavior of asset prices, in particular share prices on stock markets. This practice has its basis in the presumption that investors act rationally and without biases, and that at any moment they estimate the value of an asset based on future expectations.

Share capital

A corporation's share capital, commonly referred to as capital stock in the United States, is the portion of a corporation's equity that has been derived by the issue of shares in the corporation to a shareholder, usually for cash. "Share capital" may also denote the number and types of shares that compose a corporation's share structure. In accounting, the share capital of a corporation is the nominal value of issued shares (that is, the sum of their par values, sometimes indicated on share certificates).

Chat room

The term chat room, or chatroom (and sometimes group chat; abbreviated as GC), is primarily used to describe any form of synchronous conferencing, occasionally even asynchronous conferencing. The term can thus mean any technology, ranging from real-time online chat and online interaction with strangers (e.g., online forums) to fully immersive graphical social environments. The primary use of a chat room is to share information via text with a group of other users.

Related lectures (31)

Binary Sentiment Classifier Training

Covers the training of a binary sentiment classifier using an RNN.

Perception: Data-Driven Approaches

Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.

Autonomous Vehicles: Intelligence and Perception

Explores intelligence, perception, and AI applications in autonomous vehicles, emphasizing rational thinking and social intelligence.

Introduction to Machine Learning

Provides an overview of Machine Learning, including historical context, key tasks, and real-world applications.

Landscape and Generalisation in Deep Learning

Explores the challenges and insights of deep learning, focusing on loss landscape, generalization, and feature learning.