no code implementations • 28 Jan 2022 • Martin Bertran, Walter Talbott, Nitish Srivastava, Joshua Susskind
Learning generalizeable policies from visual input in the presence of visual distractions is a challenging problem in reinforcement learning.
1 code implementation • 2 Dec 2021 • Nitish Srivastava, Walter Talbott, Martin Bertran Lopez, Shuangfei Zhai, Josh Susskind
Modeling the world can benefit robot learning by providing a rich training signal for shaping an agent's latent state space.
no code implementations • 29 Sep 2021 • Shuangfei Zhai, Walter Talbott, Nitish Srivastava, Chen Huang, Hanlin Goh, Ruixiang Zhang, Joshua M. Susskind
We introduce Dot Product Attention Free Transformer (DAFT), an efficient variant of Transformers \citep{transformer} that eliminates the query-key dot product in self attention.
Ranked #620 on Image Classification on ImageNet
6 code implementations • 28 May 2021 • Shuangfei Zhai, Walter Talbott, Nitish Srivastava, Chen Huang, Hanlin Goh, Ruixiang Zhang, Josh Susskind
We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention.
2 code implementations • 17 May 2021 • Yue Wu, Shuangfei Zhai, Nitish Srivastava, Joshua Susskind, Jian Zhang, Ruslan Salakhutdinov, Hanlin Goh
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.
1 code implementation • ICCV 2021 • Terrance DeVries, Miguel Angel Bautista, Nitish Srivastava, Graham W. Taylor, Joshua M. Susskind
In this paper, we introduce Generative Scene Networks (GSN), which learns to decompose scenes into a collection of many local radiance fields that can be rendered from a free moving camera.
Ranked #1 on Scene Generation on VizDoom
no code implementations • 1 Jan 2021 • Yue Wu, Shuangfei Zhai, Nitish Srivastava, Joshua M. Susskind, Jian Zhang, Ruslan Salakhutdinov, Hanlin Goh
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.
no code implementations • 27 Jun 2020 • Miguel Angel Bautista, Walter Talbott, Shuangfei Zhai, Nitish Srivastava, Joshua M. Susskind
State-of-the-art learning-based monocular 3D reconstruction methods learn priors over object categories on the training set, and as a result struggle to achieve reasonable generalization to object categories unseen during training.
2 code implementations • ICLR 2020 • Yao-Hung Hubert Tsai, Nitish Srivastava, Hanlin Goh, Ruslan Salakhutdinov
We introduce a new routing algorithm for capsule networks, in which a child capsule is routed to a parent based only on agreement between the parent's state and the child's vote.
no code implementations • 6 Dec 2019 • Nitish Srivastava, Hanlin Goh, Ruslan Salakhutdinov
The pose encodes where the entity is, while the feature encodes what it is.
no code implementations • 25 Mar 2015 • Elman Mansimov, Nitish Srivastava, Ruslan Salakhutdinov
We propose a new way of incorporating temporal information present in videos into Spatial Convolutional Neural Networks (ConvNets) trained on images, that avoids training Spatio-Temporal ConvNets from scratch.
no code implementations • 13 Mar 2015 • Shengxin Zha, Florian Luisier, Walter Andrews, Nitish Srivastava, Ruslan Salakhutdinov
Our proposed late fusion of CNN- and motion-based features can further increase the mean average precision (mAP) on MED'14 from 34. 95% to 38. 74%.
10 code implementations • 16 Feb 2015 • Nitish Srivastava, Elman Mansimov, Ruslan Salakhutdinov
We further evaluate the representations by finetuning them for a supervised learning problem - human action recognition on the UCF-101 and HMDB-51 datasets.
no code implementations • Journal of Machine Learning Research 2014 • Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov
The key idea is to randomly drop units (along with their connections) from the neural network during training.
no code implementations • NeurIPS 2014 • Yichuan Tang, Nitish Srivastava, Ruslan Salakhutdinov
Our model is a proper graphical model where the 2D Similarity transformation is a part of the top-down process.
no code implementations • NeurIPS 2013 • Nitish Srivastava, Ruslan R. Salakhutdinov
The tree structure can be used to impose a generative prior over classification parameters.
Ranked #183 on Image Classification on CIFAR-100
no code implementations • 26 Sep 2013 • Nitish Srivastava, Ruslan R. Salakhutdinov, Geoffrey E. Hinton
We introduce a Deep Boltzmann Machine model suitable for modeling and extracting latent semantic representations from a large unstructured collection of documents.
no code implementations • NeurIPS 2012 • Nitish Srivastava, Ruslan R. Salakhutdinov
Our experimental results on bi-modal data consisting of images and text show that the Multimodal DBM can learn a good generative model of the joint space of image and text inputs that is useful for information retrieval from both unimodal and multimodal queries.
11 code implementations • 3 Jul 2012 • Geoffrey E. Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, Ruslan R. Salakhutdinov
When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data.
Ranked #205 on Image Classification on CIFAR-10