User profiles for N. Srivastava

Nitish Srivastava

- Verified email at cs.toronto.edu - Cited by 71498

Neha srivastava

- Verified email at hyderabad.bits-pilani.ac.in - Cited by 9318

Nikhil Srivastava

- Verified email at berkeley.edu - Cited by 3981

Novel biofiltration methods for the treatment of heavy metals from industrial wastewater

NK Srivastava, CB Majumder - Journal of hazardous materials, 2008 - Elsevier
Most heavy metals are well-known toxic and carcinogenic agents and when discharged into
the wastewater represent a serious threat to the human population and the fauna and flora …

Biological remediation technologies for dyes and heavy metals in wastewater treatment: New insight

…, A Alhazmi, S Haque, T Yoon, N Srivastava… - Bioresource …, 2022 - Elsevier
The pollution of the environment caused by dyes and heavy metals emitted by industries
has become a worldwide problem. The development of efficient, environmentally acceptable, …

Carbon nanomaterials for next-generation interconnects and passives: Physics, status, and prospects

H Li, C Xu, N Srivastava… - IEEE Transactions on …, 2009 - ieeexplore.ieee.org
… All zz-CNTs have indexes n or m = 0, while ac-CNTs have n = m. The two cases shown in …
along the lattice vectors (n or m = 0) or along the exact direction between two vectors (n = m). …

Improving neural networks by preventing co-adaptation of feature detectors

GE Hinton, N Srivastava, A Krizhevsky… - arXiv preprint arXiv …, 2012 - arxiv.org
… In networks with a single hidden layer of N units and a “softmax” output layer for computing
the probabilities of the class labels, using the mean network is exactly equivalent to taking the …

[PDF][PDF] Dropout: a simple way to prevent neural networks from overfitting

N Srivastava, G Hinton, A Krizhevsky… - The journal of machine …, 2014 - jmlr.org
… A neural net with n units, can be seen as a collection of 2n possible thinned neural networks.
These networks all share weights so that the total number of parameters is still O(n2), or …

Unsupervised learning of video representations using lstms

N Srivastava, E Mansimov… - … on machine learning, 2015 - proceedings.mlr.press
We use 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 …

[PDF][PDF] Neural networks for machine learning lecture 6a overview of mini-batch gradient descent

G Hinton, N Srivastava, K Swersky - Cited on, 2012 - cs.toronto.edu
• The standard momentum method first computes the gradient at the current location and
then takes a big jump in the direction of the updated accumulated gradient.• Ilya Sutskever(…

Multimodal learning with deep boltzmann machines

N Srivastava, RR Salakhutdinov - Advances in neural …, 2012 - proceedings.neurips.cc
We propose a Deep Boltzmann Machine for learning a generative model of multimodal data.
We show how to use the model to extract a meaningful representation of multimodal data. …

Graph sparsification by effective resistances

DA Spielman, N Srivastava - Proceedings of the fortieth annual ACM …, 2008 - dl.acm.org
… In fact, we do something stronger: we build a O(log nn matrix Z from which the effective
resistance between any two vertices (including vertices not connected by an edge) can be …

Azure accelerated networking:{SmartNICs} in the public cloud

…, M Shaw, G Silva, M Sivakumar, N Srivastava… - … USENIX Symposium on …, 2018 - usenix.org
Modern cloud architectures rely on each server running its own networking stack to implement
policies such as tunneling for virtual networks, security, and load balancing. However, …