#### Filter Results:

#### Publication Year

2011

2017

#### Publication Type

#### Co-author

#### Publication Venue

#### Key Phrases

Learn More

- Mariusz Bojarski, Davide Del Testa, +10 authors Karol Zieba
- ArXiv
- 2016

We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data from humans the system learns to drive in traffic on local roads with or without lane markings and on highways. It also operates in areas with… (More)

- Cijo Jose, Prasoon Goyal, Parv Aggrwal, Manik Varma
- ICML
- 2013

Our objective is to speed up non-linear SVM prediction while maintaining classification accuracy above an acceptable limit. We generalize Localized Multiple Kernel Learning so as to learn a tree-based primal feature embedding which is high dimensional and sparse. Primal based classification decouples prediction costs from the number of support vectors and… (More)

- Happy Mittal, Prasoon Goyal, Vibhav Gogate, Parag Singla
- NIPS
- 2014

Lifted inference algorithms for probabilistic first-order logic frameworks such as Markov logic networks (MLNs) have received significant attention in recent years. These algorithms use so called lifting rules to identify symmetries in the first-order representation and reduce the inference problem over a large probabilistic model to an inference problem… (More)

- Corinna Cortes, Prasoon Goyal, Vitaly Kuznetsov, Mehryar Mohri
- FE@NIPS
- 2015

This paper studies a new framework for learning a predictor in the presence of multiple kernel functions where the learner selects or extracts several kernel functions from potentially complex families and finds an accurate predictor defined in terms of these functions. We present an algorithm , Voted Kernel Regularization, that provides the flexibility of… (More)

- Prasoon Goyal, Zhiting Hu, Xiaodan Liang, Chenyu Wang, Eric P. Xing
- ArXiv
- 2017

The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich repre-sentational power of neural networks with Bayesian methods. However, most work on VAEs use a rather simple prior over the latent variables such as standard normal distribution , thereby restricting its applications to relatively simple… (More)

- Prasoon Goyal, Sahil Goel
- 2015

We propose a novel GPU variant for genetic algorithm that uses constant memory effectively to store and share the elite population across different blocks to obtain faster convergence rates. We compare our algorithm to a previous work which does not use constant memory, and show that using constant memory significantly improves the quality of solution for a… (More)

- Prasoon Goyal, Sahil Goel, Kshitiz Sethia
- 2015

With the increasing amount of textual data, automatic summarization has become an important task in natural language processing. In this work, we consider the summarization of Wikipedia articles, using graph-based and machine learning approaches. We obtain results comparable to an approximately-optimal summary.

- Corinna Cortes, Prasoon Goyal, Vitaly Kuznetsov, Mehryar Mohri
- ArXiv
- 2015

This paper presents an algorithm, Voted Kernel Regularization , that provides the flexibility of using potentially very complex kernel functions such as predictors based on much higher-degree polynomial kernels, while benefitting from strong learning guarantees. The success of our algorithm arises from derived bounds that suggest a new regularization… (More)

Here the first two formulas are as considered earlier in the main text. We have also added another formula R(W) to the theory. Let the domain of each of the variables be ∆ = {a, b, c}. This theory consists of 3 equivalence classes given by E

- Prasoon Goyal
- 2014

Support Vector Machines (SVMs) are state-of-the-art algorithms for classification in machine learning. However, the SVM formulation does not directly seek to find sparse solutions. In this work, we propose an alternate formulation that explicitly imposes sparsity. We show that the proposed technique is related to the standard SVM formulation and therefore… (More)