[Workshop] MLTrain: TensorFlow, Keras: Intro and Advanced Deep Learning Apps

MLTrain (http://mltrain.cc/) is coming back to NY for another training event.

Nick Vasiloglou (https://www.linkedin.com/in/vasiloglou/) and Alex Dimakis (https://www.linkedin.com/in/alex-dimakis-b1b20320/) will cover several Machine Learning and TensorFlow topics.

We have prepared a 2 day curriculum.

You can register for each day individually or for both days.

The space is offered by Ebay!

When:

June 2 - June 3, 2017, 9:00am ET to 2:00pm ET

Where:

625 6th Ave (between 18th & 19th), 3rd floor
New York, NY (Ebay)

RSVP Here:

https://www.eventbrite.com/e/mltrain-new-york-62-63-2017-tickets-33691318641?discount=fregly15

Day 1: June 2, 2017

Introduction to TensorFlow and Keras

This session is intended for beginners.

• The only requirements are:

• Be familiar with python programming

• Be able to install tensorFlow before the class date

• Be familiar with basic Machine Learning Principles

After the completion of the session you will know the basic functionality of TensorFlow. You will be able to build simple models and also use it in data science projects.

Introduction to TensorFlow

• MLTrain Introduction

• Tensors Basics

• Computational Graph Model

• Graph Inspection & Visualization with TensorBoard

• Basic Ops

Linear Algebra

• Fundamentals of Linear Algebra

• Least Square Problem

• Manipulating Matrices in TensorFlow

• Sparse/Dense Matrix/Vectors Operations

• Limitations of TF

Overview of the tf.contrib.learn package

• The Estimator class

• Feature Columns and Feature Engineering

• input_processing

• linear Estimators in tf.contrib.learn

• Explicit kernel methods

• training deep models in tf.contrib.learn

• Logging and monitoring

• Keras

Optimization In TensorFlow

• Objective Function

• Gradients Computation

• The tf.Optimizer Class

• Predefined Optimizers

• TF Linear Regression Model In 3 Lines

• Predefined Losses

Introduction to Neural Networks

• Fundamentals of Neural Nets

• The back propagation algorithm

• Convolutional Nets

• Recurrent Neural Nets

• Applications

Day 1: June 2, 2017

Advanced Deep Learning Topics

In this session you will be exposed to modern machine learning papers.In order to attend this session you are expected:

• To have basic knowledge of TensorFlow. You can do that by going through the tutorials in the www.tensorflow.org (http://www.tensorflow.org/)

• To be proficient in python

• To have tensorFlow already installed on your machine

• To have basic understanding of machine learning methods

• Kernel Methods in TensorFlow

• Pixel Recurrent Neural Networks (https://arxiv.org/abs/1601.06759)

• Memory Networks (http://arxiv.org/abs/1503.08895v4)

• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks (https://arxiv.org/abs/1703.05192)

Day 2: June 3, 2017

Deep Learning Applications

In this session you will learn how to use TensorFlow for building deep learning models for different application domains. The session emphasizes understanding models, how to use them and when to trust them.

In order to attend this session you are expected:

• To have basic knowledge of TensorFlow. You can do that by going through the tutorials in the www.tensorflow.org (http://www.tensorflow.org/)

• To be proficient in python

• To have tensorFlow already installed on your machine

• To have some data science prior experience or exposure

Working with Images

• Understanding and using Generative Models

• The Generative Adversarial Network (GAN)

• Applications of GANs

Working with Text

• Word2Vec

• LSTMs for parsing Text

Deep Reinforcement Learning

• Encoding Agents for playing Games

• Policy learning

RSVP Here: https://www.eventbrite.com/e/mltrain-new-york-62-63-2017-tickets-33691318641?discount=fregly15