Related papers: Unsupervised Intuitive Physics from Past Experienc…

Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations. Meta-imitation learning is a promising approach towards…

The traditional pedagogical paradigm in physics is based on a deductive approach. However, with the recent advances in information technology, we are facing a dramatic increase in the amount of readily available information; hence, the…

Human actions are comprised of a sequence of poses. This makes videos of humans a rich and dense source of human poses. We propose an unsupervised method to learn pose features from videos that exploits a signal which is complementary to…

Learning is an inherently continuous phenomenon. When humans learn a new task there is no explicit distinction between training and inference. As we learn a task, we keep learning about it while performing the task. What we learn and how we…

We consider the problem of learning useful robotic skills from previously collected offline data without access to manually specified rewards or additional online exploration, a setting that is becoming increasingly important for scaling…

Traditional machine learning relies on explicit models and domain assumptions, limiting flexibility and interpretability. We introduce a model-free framework using surprisal (information theoretic uncertainty) to directly analyze and…

Reprogrammable mechanical metamaterials, composed of a lattice of discretely adaptive elements, are emerging as a promising platform for mechanical intelligence. To operate in unknown environments, such structures must go beyond passive…

Evolution has resulted in highly developed abilities in many natural intelligences to quickly and accurately predict mechanical phenomena. Humans have successfully developed laws of physics to abstract and model such mechanical phenomena.…

We introduce a self-supervised method for learning visual correspondence from unlabeled video. The main idea is to use cycle-consistency in time as free supervisory signal for learning visual representations from scratch. At training time,…

We present a method to learn the 3D surface of objects directly from a collection of images. Previous work achieved this capability by exploiting additional manual annotation, such as object pose, 3D surface templates, temporal continuity…

Wooden blocks are a common toy for infants, allowing them to develop motor skills and gain intuition about the physical behavior of the world. In this paper, we explore the ability of deep feed-forward models to learn such intuitive…

Unsupervised learning is a discipline of machine learning which aims at discovering patterns in big data sets or classifying the data into several categories without being trained explicitly. We show that unsupervised learning techniques…

In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense representation from an image, by randomly sampling and…

Reasoning about objects, relations, and physics is central to human intelligence, and a key goal of artificial intelligence. Here we introduce the interaction network, a model which can reason about how objects in complex systems interact,…

Based on life-long observations of physical, chemical, and biologic phenomena in the natural world, humans can often easily picture in their minds what an object will look like in the future. But, what about computers? In this paper, we…

Predicting the future interaction of objects when they come into contact with their environment is key for autonomous agents to take intelligent and anticipatory actions. This paper presents a perception framework that fuses visual and…

Unsupervised learning poses one of the most difficult challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large quantities of unlabeled…

We propose a strong baseline model for unsupervised feature learning using video data. By learning to predict missing frames or extrapolate future frames from an input video sequence, the model discovers both spatial and temporal…

An unsupervised shape analysis is proposed to learn concepts reflecting shape commonalities. Our approach is two-fold: i) a spatial topology analysis of point cloud segment constellations within objects is used in which constellations are…

We propose HyperDynamics, a dynamics meta-learning framework that conditions on an agent's interactions with the environment and optionally its visual observations, and generates the parameters of neural dynamics models based on inferred…