Bharat Kaul

is this you? claim profile

0 followers
Intel

PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitives

Deep Neural Networks (DNNs) have revolutionized many aspects of our live...
06/02/2020 ∙ by Sanket Tavarageri, et al. ∙ 0 ∙ share

read it
PolyScientist: Automatic Loop Transformations Combined with Microkernels for Optimization of Deep Learning Primitives

At the heart of deep learning training and inferencing are computational...
02/06/2020 ∙ by Sanket Tavarageri, et al. ∙ 0 ∙ share

read it
SEERL: Sample Efficient Ensemble Reinforcement Learning

Ensemble learning is a very prevalent method employed in machine learnin...
01/15/2020 ∙ by Rohan Saphal, et al. ∙ 43 ∙ share

read it
K-TanH: Hardware Efficient Activations For Deep Learning

We propose K-TanH, a novel, highly accurate, hardware efficient approxim...
09/17/2019 ∙ by Abhisek Kundu, et al. ∙ 0 ∙ share

read it
High Performance Scalable FPGA Accelerator for Deep Neural Networks

Low-precision is the first order knob for achieving higher Artificial In...
08/29/2019 ∙ by Sudarshan Srinivasan, et al. ∙ 0 ∙ share

read it
Automatic Model Parallelism for Deep Neural Networks with Compiler and Hardware Support

The deep neural networks (DNNs) have been enormously successful in tasks...
06/11/2019 ∙ by Sanket Tavarageri, et al. ∙ 0 ∙ share

read it
Mixed Precision Training With 8-bit Floating Point

Reduced precision computation for deep neural networks is one of the key...
05/29/2019 ∙ by Naveen Mellempudi, et al. ∙ 0 ∙ share

read it
A Study of BFLOAT16 for Deep Learning Training

This paper presents the first comprehensive empirical study demonstratin...
05/29/2019 ∙ by Dhiraj Kalamkar, et al. ∙ 0 ∙ share

read it
Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers

As deep learning methods form a critical part in commercially important ...
09/04/2018 ∙ by Apoorv Vyas, et al. ∙ 0 ∙ share

read it
Mixed Precision Training of Convolutional Neural Networks using Integer Operations

The state-of-the-art (SOTA) for mixed precision training is dominated by...
02/03/2018 ∙ by Dipankar Das, et al. ∙ 0 ∙ share

read it
On Scale-out Deep Learning Training for Cloud and HPC

The exponential growth in use of large deep neural networks has accelera...
01/24/2018 ∙ by Srinivas Sridharan, et al. ∙ 0 ∙ share

read it
RAIL: Risk-Averse Imitation Learning

Imitation learning algorithms learn viable policies by imitating an expe...
07/20/2017 ∙ by Anirban Santara, et al. ∙ 0 ∙ share

read it
Ternary Residual Networks

Sub-8-bit representation of DNNs incur some discernible loss of accuracy...
07/15/2017 ∙ by Abhisek Kundu, et al. ∙ 0 ∙ share

read it
Ternary Neural Networks with Fine-Grained Quantization

We propose a novel fine-grained quantization (FGQ) method to ternarize p...
05/02/2017 ∙ by Naveen Mellempudi, et al. ∙ 0 ∙ share

read it
Mixed Low-precision Deep Learning Inference using Dynamic Fixed Point

We propose a cluster-based quantization method to convert pre-trained fu...
01/31/2017 ∙ by Naveen Mellempudi, et al. ∙ 0 ∙ share

read it

Bharat Kaul

Featured Co-authors

Balaraman Ravindran

Dipankar Das

Dheevatsa Mudigere

Pradeep Dubey

Theodore L. Willke

Jiyan Yang

Sasikanth Avancha

Jongsoo Park

Alexander Heinecke

Jianyu Huang

Abhisek Kundu

PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitives

PolyScientist: Automatic Loop Transformations Combined with Microkernels for Optimization of Deep Learning Primitives

SEERL: Sample Efficient Ensemble Reinforcement Learning

K-TanH: Hardware Efficient Activations For Deep Learning

High Performance Scalable FPGA Accelerator for Deep Neural Networks

Automatic Model Parallelism for Deep Neural Networks with Compiler and Hardware Support

Mixed Precision Training With 8-bit Floating Point

A Study of BFLOAT16 for Deep Learning Training

Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers

Mixed Precision Training of Convolutional Neural Networks using Integer Operations

On Scale-out Deep Learning Training for Cloud and HPC

RAIL: Risk-Averse Imitation Learning

Ternary Residual Networks

Ternary Neural Networks with Fine-Grained Quantization

Mixed Low-precision Deep Learning Inference using Dynamic Fixed Point