Off the shelf deep neural network models for the Edge

Off the shelf deep neural network models for the Edge

Off the shelf deep neural network models for the EdgeOff the shelf deep neural network models for the EdgeOff the shelf deep neural network models for the Edge

Leadership Team

Amit Mate

image1

 Founder & CEO  

 

 Amit has 20+ years of experience in leading cross-functional Engineering  teams  on ML and Wireless projects from concept-through-commercialization. He has delivered commercial grade software on several deep-technologies (OCR, 3G/4G, VR, Femtocells)  with Industry leaders such as Qualcomm and Nokia.

 

Amit earned his master’s degree in electrical communication engineering from  IISc, Bangalore and bachelor's in electronics and communication from NIT, Nagpur. He has been awarded 10+ patents including 3GPP essential patents.

 

 

What we do?

A trained neural network model is the essence of ML inferencing software. It is a compact form of software that encompasses and accomplishes difficult tasks such as detection, classification & recognition for image, audio, video or text. Our models will enable intelligent tasks on edge devices of today and tomorrow.

How we do it ?

Neural Network Model Design and Architecture

We provide innovative network models  designed to fit your embedded platform constraints of processor speed, SRAM and flash size and ML software library availability

Network Training and Datasets

We take care of training network models and building datasets and provide ready to deploy modules for your embedded platform with state of the art performance

Plug and play models

We deliver validated network models  tested on target platforms with real world data

GI News