The Omniglot challenge: a 3-year progress report (2019-02-09T00:00:00.000000Z)

TL;DR

It is concluded that recent approaches are still far from human-like concept learning on Omniglot, a challenge that requires performing many tasks with a single model.

Authors

R. Salakhutdinov

32 papers

B. Lake

5 papers

J. Tenenbaum

25 papers

TL;DR

Authors

References36 items

Artificial Intelligence Hits the Barrier of Meaning

Building Machines that Learn and Think Like People

Synthesizing Programs for Images using Reinforced Adversarial Learning

The Variational Homoencoder: Learning to learn high capacity generative models from few examples

A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs

Building Machines that Learn and Think for Themselves: Commentary on Lake et al., Behavioral and Brain Sciences, 2017

Few-Shot Learning with Graph Neural Networks

Prototypical Networks for Few-shot Learning

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

Attentive Recurrent Comparators

Active One-shot Learning

Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes

Meta-Learning with Memory-Augmented Neural Networks

Matching Networks for One Shot Learning

Towards a Neural Statistician

Towards Conceptual Compression

Attend, Infer, Repeat: Fast Scene Understanding with Generative Models

One-Shot Generalization in Deep Generative Models

Human-level concept learning through probabilistic program induction

Human-level control through deep reinforcement learning

DRAW: A Recurrent Neural Network For Image Generation

ImageNet classification with deep convolutional neural networks

The Arcade Learning Environment: An Evaluation Platform for General Agents

ImageNet: A large-scale hierarchical image database

Inferring Motor Programs from Images of Handwritten Digits

The Big Book of Concepts

Object name Learning Provides On-the-Job Training for Attention

A personal communication

A Study of Thinking

Ingredients of intelligence: from classic debates to an engineering roadmap

Building on prior knowledge without building it in

Causal generative models are just a start

Siamese Neural Networks for One-Shot Image Recognition

Concept learning as motor program induction: A large-scale empirical study

Metamagical Themas: Questing for the Essence of Mind and Pattern

Learning and memorization of classifications.

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names