User profiles for Josh Tenenbaum
 | Joshua B. TenenbaumMIT Verified email at mit.edu Cited by 107248 |
Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation
…, A Saeedi, J Tenenbaum - Advances in neural …, 2016 - proceedings.neurips.cc
Learning goal-directed behavior in environments with sparse feedback is a major challenge
for reinforcement learning algorithms. One of the key difficulties is insufficient exploration, …
for reinforcement learning algorithms. One of the key difficulties is insufficient exploration, …
Building machines that learn and think like people
Recent progress in artificial intelligence has renewed interest in building systems that learn
and think like people. Many advances have come from using deep neural networks trained …
and think like people. Many advances have come from using deep neural networks trained …
End-to-end differentiable physics for learning and control
We present a differentiable physics engine that can be integrated as a module in deep
neural networks for end-to-end learning. As a result, structured physics knowledge can be …
neural networks for end-to-end learning. As a result, structured physics knowledge can be …
[PDF][PDF] Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling
We study the problem of 3D object generation. We propose a novel framework, namely 3D
Generative Adversarial Network (3D-GAN), which generates 3D objects from a probabilistic …
Generative Adversarial Network (3D-GAN), which generates 3D objects from a probabilistic …
Machine behaviour
Abstract Machines powered by artificial intelligence increasingly mediate our social, cultural,
economic and political interactions. Understanding the behaviour of artificial intelligence …
economic and political interactions. Understanding the behaviour of artificial intelligence …
A critical period for second language acquisition: Evidence from 2/3 million English speakers
Children learn language more easily than adults, though when and why this ability declines
have been obscure for both empirical reasons (underpowered studies) and conceptual …
have been obscure for both empirical reasons (underpowered studies) and conceptual …
Neural-symbolic vqa: Disentangling reasoning from vision and language understanding
We marry two powerful ideas: deep representation learning for visual recognition and
language understanding, and symbolic program execution for reasoning. Our neural-symbolic …
language understanding, and symbolic program execution for reasoning. Our neural-symbolic …
Galileo: Perceiving physical object properties by integrating a physics engine with deep learning
…, JJ Lim, B Freeman, J Tenenbaum - Advances in neural …, 2015 - proceedings.neurips.cc
Humans demonstrate remarkable abilities to predict physical events in dynamic scenes,
and to infer the physical properties of objects from static images. We propose a generative …
and to infer the physical properties of objects from static images. We propose a generative …
Deep convolutional inverse graphics network
This paper presents the Deep Convolution Inverse Graphics Network (DC-IGN), a model that
aims to learn an interpretable representation of images, disentangled with respect to three-…
aims to learn an interpretable representation of images, disentangled with respect to three-…
One-shot learning by inverting a compositional causal process
…, RR Salakhutdinov, J Tenenbaum - Advances in neural …, 2013 - proceedings.neurips.cc
People can learn a new visual class from just one example, yet machine learning algorithms
typically require hundreds or thousands of examples to tackle the same problems. Here we …
typically require hundreds or thousands of examples to tackle the same problems. Here we …