Mengye Ren - Towards Continual and Compositional Few-shot Learning

Показать описание

September 22, 2020. MIT CSAIL

Abstract: Few-shot learning has recently emerged as a popular area of research towards building more flexible machine learning programs that can adapt at test time. However, it now faces two major criticisms. First, the “k-shot n-way” episodic structure is still far from modelling the incremental knowledge acquisition procedure of an agent in a natural environment. Secondly, there has been limited improvement towards modelling compositional understanding of novel objects; on the other hand, features obtained from regular classification tasks can perform very well. In this talk I will introduce two recent advances that address each of the challenges above.

Bio: Mengye Ren is a PhD student in the machine learning group of the Department of Computer Science at the University of Toronto. His academic advisor is Prof. Richard Zemel. He also works as a research scientist at Uber Advanced Technologies Group (ATG) Toronto, directed by Prof. Raquel Urtasun, doing self-driving related research. His research interests are meta-learning, few-shot learning, and continual learning. He studied undergrad in Engineering Science at the University of Toronto.

Vision & Graphics Seminar at MIT

Рекомендации по теме

Mengye Ren - Towards Continual and Compositional Few-shot Learning

Mengye Ren - Towards Continual and Compositional Few-shot Learning

Towards Continual and Compositional Few shot Learning

Mengye Ren: Lifelong Learning in Structured Environments

Meta Learning Within a Lifetime

Lifelong Learning in Structured Environments

[Continual Learning Course] Lecture #4: Evaluation & Metrics

Explainable, Adaptive, and Cross-Domain Few-Shot Learning (Part 1) - Dr. Leonid Karlinsky

[Continual Learning Course] Lecture #8: Frontiers of Continual Learning

Instance Credibility Inference for Few-Shot Learning

Maria Rigaki & Elnaz Babyeva | Forget Me Not: Malware Classification as a Continual Learning Pro...

SDFVAE: Static and Dynamic Factorized VAE for Anomaly Detection of Multivariate CDN KPIs

[CVPR20] Compositional Convolutional Neural Networks: A Deep Net with Innat Robustness to Occlusion

ContinualAI RG: 'Linear Mode Connectivity in Multitask and Continual Learning'

ContinualAI Reading Group: 'Defining Benchmarks for Continual Few-Shot Learning'

Image Super-Resolution and AI | Radu Timofte is Humboldt professor for AI

Research talk: Bucket of me: Using few-shot learning to realize teachable AI systems

CLVision Poster: 'Avalanche: an End-to-End Library for Continual Learning'

Reza Azad: Few-shot Continual Learning

ContinualAI Seminars: 'Reducing Representation Drift in Online Continual Learning'

Face Attributes | Lecture 40 (Part 2) | Applied Deep Learning (Supplementary)

Compositional Generalizability in Geometry, Physics, and Policy Learning

3DQ-Nets: Visual Concepts Emerge in Pose Equivariant 3D Quantized Neural Scene Representations

Meta-Graph: Few-Shot Link Prediction Using Meta-Learning | AISC

ContinualAI Meetup: 'Generalization and Robustness in Continual Learning'