Stepping Forward on the Last Mile

no code implementations • 6 Nov 2024 • Chen Feng, Shaojie Zhuo, Xiaopeng Zhang, Ramchalam Kinattinkara Ramakrishnan, Zhaocong Yuan, Andrew Zou Li

Our results demonstrate that on the last mile of model customization on edge devices, training with fixed-point forward gradients is a feasible and practical approach.

An Empirical Study of Low Precision Quantization for TinyML

no code implementations • 10 Mar 2022 • Shaojie Zhuo, Hongyu Chen, Ramchalam Kinattinkara Ramakrishnan, Tommy Chen, Chen Feng, Yicheng Lin, Parker Zhang, Liang Shen

In this study, we focus on post-training quantization (PTQ) algorithms that quantize a model to low-bit (less than 8-bit) precision with only a small set of calibration data and benchmark them on different tinyML use cases.

BIG-bench Machine Learning Model Compression +1

Differentiable Mask for Pruning Convolutional and Recurrent Networks

no code implementations • 10 Sep 2019 • Ramchalam Kinattinkara Ramakrishnan, Eyyüb Sari, Vahid Partovi Nia

Pruning is one of the most effective model reduction techniques.

Model Compression Multi-Task Learning +1

Deep Demosaicing for Edge Implementation

no code implementations • 26 Mar 2019 • Ramchalam Kinattinkara Ramakrishnan, Shangling Jui, Vahid Patrovi Nia

We provide an exhaustive search of deep neural network architectures and obtain a pareto front of Color Peak Signal to Noise Ratio (CPSNR) as the performance criterion versus the number of parameters as the model complexity that beats the state-of-the-art.

Demosaicking Neural Architecture Search