Deepak ManglainHeartbeatPractical tips for better quantization resultsQuantization can make your ML models smaller, faster, and more energy-efficient.Sep 21, 2020Sep 21, 2020
Deepak ManglainHeartbeatQuantization ArithmeticDiving deep into the model compression techniqueAug 14, 2020Aug 14, 2020
Deepak ManglainHeartbeatThe Engineering Behind ConvolutionsExploring ways to optimize convolutions for deep learning modelsMar 16, 2020Mar 16, 2020
Deepak ManglaDesigning Faster Neural Networks4 tips to make smaller and faster neural networks.Feb 26, 20203Feb 26, 20203
Deepak ManglaUnderstanding ‘Winograd Fast Convolution’Deep learning thrives on speed. Here we will discuss how we can improve convolution by factor of 2.5x .Jul 18, 20193Jul 18, 20193