Deep Learning: TensorFlow 2.0 vs PyTorch

This is a past event

100 people went

Location image of event venue

Details

Please sign in at the front desk.

PLEASE NOTE: Tonight's event is at capacity. If you are not registered for the event you can find the event being Livestreamed here: https://livestream.com/metis/events/8776155

Facilitated by the confluence of inexpensive computing power, unprecedentedly large data sets, and clever theoretical advances, Deep Learning algorithms are driving the contemporary revolution in Artificial Intelligence. Deep Learning has emerged as uniquely influential across a broad range of applications, including classification (e.g., visual recognition, sentiment analysis), prediction (e.g., stock markets, health outcomes), generation (e.g., creating works of art, composing music), and sequential decision-making (e.g., games, robotics). In the past few years, Deep Neural Networks have made their way into countless everyday applications, including Tesla’s Autopilot, Amazon's Alexa, and Google's suggested email replies. Indeed, Deep Learning algorithms have exceeded human performance on previously intractable computational problems like language translation, object detection, and the game of Go.

This talk begins with a survey of the primary families of Deep Learning approaches: Convolutional Neural Networks, Recurrent Neural Networks, Generative Adversarial Networks, and Deep Reinforcement Learning. Via interactive Jupyter notebook demos in Python, the meat of the talk will appraise the two leading Deep Learning libraries: TensorFlow and PyTorch. With respect to both model development and production deployment, the strengths and weaknesses of the two libraries will be covered -- with a particular focus on the upcoming TensorFlow 2.0 release that integrates core TensorFlow with the high-level Keras API. The talk will conclude with Q&A as well as a book-signing session for Deep Learning Illustrated, Dr. Krohn's new book.

Jon Krohn is Chief Data Scientist at the machine learning company untapt. He is the presenter of a popular series of tutorials on artificial neural networks, including Deep Learning with TensorFlow, and is the author of Deep Learning Illustrated, released by Pearson in 2019. Jon holds a doctorate in neuroscience from Oxford University and has been publishing on machine learning in leading academic journals since 2010. He provides a comprehensive deep learning curriculum at the NYC Data Science Academy, guest lectures at Columbia University and, along with researchers from the university's Irving Medical Center, holds a National Institutes of Health grant to automate medical image processing with deep learning.

*************

About Metis

Metis (https://thisismetis.com/) accelerates data science learning for individuals, companies, and institutions through corporate training and accredited, immersive bootcamps.

The Metis bootcamp curriculum is designed and delivered by highly educated and industry-experienced practitioners, and all bootcamp graduates receive hands-on career support until they’re hired. Campuses are located in Chicago, New York City and San Francisco.

On the corporate side, Metis works with large organizations who want to upskill their teams in data science and analytics to gain efficiencies, remain competitive, and improve their bottom lines. Metis is proud to be backed by Kaplan, a global leader in education.

*************

Join our Metis Community Slack channel!

Apply here: http://bit.ly/MetisCommunitySlack

*************

Metis Code of Conduct

Metis is dedicated to providing a harassment-free experience for everyone, regardless of gender identity, age, sexual orientation, disability, physical appearance, body size, race, or religion (or lack thereof).

We do not tolerate harassment of students, staff, or visitors in any form. Sexual language and imagery is not appropriate for any event including talks, workshops, parties, and other online media. Individuals and groups that do not abide by these rules will be asked to leave and, if necessary, prohibited from future events.