Papers

How Evolution May Work Through Curiosity-Driven Developmental Process

Provides an overview of a curiosity-driven paradigm and relates the results back to the evolutionary process.

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans

Adversarial examples trained on an ensemble of CNNs with a retinal preprocessing layer reduce the accuracy of time-limited humans in a two alternative forced choice task.

Control What You Can: Intrinsically Motivated Task-Planning Agent

The Control What You Can (CWYC) method learns to control components of the environment to achieve multi-step goals by combining task planning with surprise and learning progress based intrinsic motivation.

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations

A large scale, comprehensive study challenges various assumptions in learning disentangled representations, which motivates demonstrating concrete benefits in robust experimental setups in future work.

Learning Physical Graph Representations from Visual Scenes

Introduces a novel hierarchical representation of visual scenes, Physical Scene Graphs (PSGs), as well as a network for learning them from RGB movies, PSGNet, which outperforms other unsupervised methods in scene segmentation.

Compositional Video Prediction

Novel method for video prediction from a single frame by decomposing the scene into entities with location and appearance features, capturing ambiguities with a global latent variable.

Embodied Multimodal Multitask Learning

Proposes multitask model to jointly learn semantic goal navigation and embodied question answering.

Automated Curriculum Learning for Neural Networks

Investigates automatically generating curricula based on a variety of progress signals that are computed for each data sample.

Toddler-Inspired Visual Object Learning

Computer vision models trained on data obtained from head-mounted cameras on children performs better than data from adults.

Automatic Goal Generation for Reinforcement Learning Agents

Applies curriculum learning to a RL context to achieve policies.