ODSC East 2019 Warm-Up Webinar

ODSC East is getting closer! We want to invite you to participate in ODSC East's Warm-Up webinar.

This event will feature four 30 minutes tutorials presented by our distinguished speakers listed below. These sessions will highlight some of the most integral topics, tools, and languages in Deep Learning and Machine Learning and give attendees a preview of what can be expected at ODSC East, Boston's largest applied data science conference.

To access this webinar, please register using the link below:
https://attendee.gotowebinar.com/register/7482285874203395331

Date: Jan 24th, 2019
Time: 1 - 3 pm EST

Full Agenda Detail:

Session 1 - Becoming The Complete Data Scientist with Data Literacy and Data Storytelling (30 Minutes)

Speaker: Dr.Kirk Borne, Principal Data Scientist

Abstract:
I will review some of the key data literacy components that contribute to successful data science in real world applications. In discussing these concepts, I will give examples through the art of data storytelling, which aims to answer the core questions that your clients, colleagues, and stakeholders want to have answered: What? So what? Now what? Your technical skills may bring you customers, but it's not the technical stuff that you know (i.e., your successes) that brings your customers back. What brings customers back is your customers' successes, which are nurtured and grown through clear explanations of the data, the modeling activities, and the results, which they can then share with others.

Session 2 - Introduction to Machine Learning (30 Minutes)

Speaker:
Andreas Mueller, Ph.D., Author, Lecturer, Core Contributor of scikit-learn

Abstract:
Machine learning has become an indispensable tool across many areas of research and commercial applications. This talk will give a general introduction to machine learning, as well as introduce practical tools for you to apply machine learning in your research. We will focus on one particularly important subfield of machine learning, supervised learning. The goal of supervised learning is to "learn" a function that maps inputs x to an output y, by using a collection of training data consisting of input-output pairs. We will walk through formalizing a problem as a supervised machine learning problem, creating the necessary training data and applying and evaluating a machine learning algorithm. The talk should give you all the necessary background to start using machine learning yourself.

Session 3 - Pre-trained models, Transfer Learning and Advanced Keras Features (30 Minutes)

Speaker:
Francesco Mosconi, Ph.D. in Physics and Data Scientist at Catalit LLC, Instructor at Udemy

Abstract:
You have been using keras for deep learning models and are ready to bring your skills to the next level. In this workshop, we will explore the use of pre-trained networks for image classification, transfer learning to adapt a pre-trained network to your use case, multi gpu training, data augmentation, keras callbacks and support for different kernels.

Session 4 - Easy Visualizations for Deep Learning (30 Minutes)

Speaker:
Douglas Blank, Senior Software Engineer at Comet.ML

Abstract:

Visualizations are important in order to debug and understand how a Deep Learning model is representing a problem. In this talk, I will introduce a layer of software (ConX) that was developed on top of Keras in Jupyter Notebooks for making useful (and beautiful) visualizations of activations of a neural network. We will develop a model from scratch, train it, test it, and explore various tools for visualizing learning over time in representational space.

ODSC Links:
• Get free access to more talks like this at LearnAI:
https://learnai.odsc.com/
• Facebook: https://www.facebook.com/OPENDATASCI/
• Twitter: https://twitter.com/odsc & @odsc
• LinkedIn: https://www.linkedin.com/company/open-data-science/
• East Conference Apr 30 - May 3: https://odsc.com/boston