Understanding and Visualizing ResNets that Forever Revolutionized Deep Learning


In December 2015, a published paper rocked the deep learning world. This paper is widely regarded as one of the most influential papers in modern deep learning and has been cited over 110,000 times. The name of this paper was Deep Residual Learning for Image Recognition (aka, the ResNet paper). In this session, we’ll take a brief tour through the history of computer vision, into the anatomy of a convolutional neural network, understand their limitations, and learn how the ResNet paper changed deep learning forever.

By the end of the session, you’ll know:

• What computer vision was like before convolutional neural networks (CNNs)
• The anatomy of CNNs
• The limitations of CNNs
• Residual networks and the skip connection
• How to perform image classification with ResNet with code

Harpreet Sahota

Harpreet Sahota

DevRel Manager at Deci AI

Harpreet Sahota is a Data Scientist, Deep Learning Practitioner, Developer Advocate, Podcast Host, MLOps Strategist, father, and husband. Harpreet worked as a Biostatistician before deciding to get back to his love of predictive modeling and computer sciences, continuing to pursue many successful career paths such as Senior Data Scientist at Bold Commerce, Lead Data Scientist at Price Industries, and Machine Learning Developer Advocate at Comet ML. You may recognize his name from the Data Science Dream Job, where he mentored around 3000 up-and-comers, or through his podcast started in 2020 called The Artists of Data Science, where he has interviewed some of the biggest names in machine learning.


We are looking for passionate people willing to cultivate and inspire the next generation of leaders in tech, business, and data science. If you are one of them get in touch with us!

Become a Presenter