activity
20152019
most citedA Study of BFLOAT16 for Deep Learning Training

66 citations · 156 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG2019

K-TanH: Efficient TanH For Deep Learning

Abhisek Kundu, Alex Heinecke, Dhiraj Kalamkar +7

We propose K-TanH, a novel, highly accurate, hardware efficient approximation of popular activation function TanH for Deep Learning. K-TanH consists of parameterized low-precision…

cs.LG201966 cited

A Study of BFLOAT16 for Deep Learning Training

Dhiraj Kalamkar, Dheevatsa Mudigere, Naveen Mellempudi +16

This paper presents the first comprehensive empirical study demonstrating the efficacy of the Brain Floating Point (BFLOAT16) half-precision format for Deep Learning training acros…

cs.IT20176 cited

Ternary Residual Networks

Abhisek Kundu, Kunal Banerjee, Naveen Mellempudi +4

Sub-8-bit representation of DNNs incur some discernible loss of accuracy despite rigorous (re)training at low-precision. Such loss of accuracy essentially makes them equivalent to…

cs.LG201761 cited

Ternary Neural Networks with Fine-Grained Quantization

Naveen Mellempudi, Abhisek Kundu, Dheevatsa Mudigere +3

We propose a novel fine-grained quantization (FGQ) method to ternarize pre-trained full precision models, while also constraining activations to 8 and 4-bits. Using this method, we…

cs.LG201723 cited

Mixed Low-precision Deep Learning Inference using Dynamic Fixed Point

Naveen Mellempudi, Abhisek Kundu, Dipankar Das +2

We propose a cluster-based quantization method to convert pre-trained full precision weights into ternary weights with minimal impact on the accuracy. In addition, we also constrai…

cs.IT2015

Recovering PCA from Hybrid- Sparse Sampling of Data Elements

Abhisek Kundu, Petros Drineas, Malik Magdon-Ismail

This paper addresses how well we can recover a data matrix when only given a few of its elements. We present a randomized algorithm that element-wise sparsifies the data, retaining…