Topics In Demand
Notification
New

No notification found.

Blog
From Human To Machine Designed Neural Architecture: Session Highlights With IBM

November 10, 2019

AI

441

0

Computer Vision related tasks include acquiring data, process, analyse and understand digital images. The application of computer vision is expansive, including Facial Recognition, Handwriting recognition, Cancer detection, Reverse Image Search & Autonomous /Self-driving vehicles / ADAS.

One crucial aspect for this progress is novel neural architectures, which have mostly been developed by human experts, and which require a tremendous amount of human effort to develop. For instance, for the task of classifying images with a deep learning model, a practitioner might need to check off a sizeable to-do list including figuring out a data augmentation policy, finding a suitable architecture for the model, finding the hyper-parameter settings for the training algorithm & addressing auxiliary practical objectives like model compression for deployment

Automated Deep Learning is concerned with automating this process by finding suitable pre-processing techniques and architecture designs along with training routines and configurations required to obtain a well-performing deep learning model. In this session, the attendees understand the basics of Neural Architecture, its automation approach and the consumption of the same through reverse Image Search.

NASSCOM CoE – IoT & AI Gurugram & IBM organised a session on Neural Architecture Search for Computer Vision on 19th October 2019.

There were over 70 attendees, focused on streamlining model training & deployment to classify images and detect objects as well as efficient Data set management and auto labelling. Attendees included advanced developers from enterprises like Accenture, Nagarro, HCL, TCS, Sapient, Ernst & Young, KPMG, Genpact, ThoughtWorks, Globallogic, Petro IT Solution, Colt, Perch Group, Telus, Xavient Digital, Seneto Network Systems, Techligent Systems. Startups that attended the session included like Nebularc, KBN Knockiot, Attentive AI, DronaMaps, Algofocus, Parkzap Labs, Vision Networkz, Cvision.ai, SpectralTech.ai, Spectross Digital Systems as well as students from University of Delhi, Indian Institute of Information Technology, KIIT College of Engg, PDM University, SRM University, Jaypee Institute of Information Technology, ABES Engineering College, Amity University and Galgotias University.

For more information, contact Shantanu Gaur (shantanu@nasscom.in)

For more updates, follow NASSCOM CoE IoT-DSAI on LinkedIn, Twitter, Facebook, and Youtube.

 


That the contents of third-party articles/blogs published here on the website, and the interpretation of all information in the article/blogs such as data, maps, numbers, opinions etc. displayed in the article/blogs and views or the opinions expressed within the content are solely of the author's; and do not reflect the opinions and beliefs of NASSCOM or its affiliates in any manner. NASSCOM does not take any liability w.r.t. content in any manner and will not be liable in any manner whatsoever for any kind of liability arising out of any act, error or omission. The contents of third-party article/blogs published, are provided solely as convenience; and the presence of these articles/blogs should not, under any circumstances, be considered as an endorsement of the contents by NASSCOM in any manner; and if you chose to access these articles/blogs , you do so at your own risk.


© Copyright nasscom. All Rights Reserved.