Nitish Srivastava

Indian Institute of Technology Roorkee | University of Roorkee · Department of Metallurgical and Materials Engineering

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. We describe several initializations of weights in 3D Convolutional Layers of Spatio-Temporal ConvNet using 2D Convolutional Weights learned...

We conduct an in-depth exploration of different strategies for doing event detection and action recognition in videos using convolutional neural networks (CNNs) trained for image classification. We study different ways of performing frame calibration, spatial and temporal pooling, feature normalization, choice of CNN layer as well as choice of clas...

We use multilayer Long Short Term Memory (LSTM) networks to learn representations of video sequences. Our model uses an encoder LSTM to map an input sequence into a fixed length representation. This representation is decoded using single or multiple decoder LSTMs to perform different tasks, such as reconstructing the input sequence, or predicting t...

A Deep Boltzmann Machine is described for learning a generative model of data that consists of multiple and diverse input modalities. The model can be used to extract a unified representation that fuses modalities together. We find that this representation is useful for classification and information retrieval tasks. The model works by learning a p...

Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for address...

Attention has long been proposed by psychologists as important for effectively dealing with the enormous sensory stimulus available in the neocortex. Inspired by visual attention models in computational neuroscience and by the need for deep generative models to learn on object-centric data, we describe a framework for generative learning using atte...

We introduce a Deep Boltzmann Machine model suitable for modeling and extracting latent semantic representations from a large unstructured collection of documents. We overcome the apparent difficulty of training a DBM with judicious parameter tying. This parameter tying enables an efficient pretraining algorithm and a state initialization scheme th...

When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of the feature detectors on each training case. This prevents complex co-adaptations in which a feature detector is only helpful in the context of several oth...