Deep Learning for Everyone
Understanding deep learning and machine learning foundations for data science
Over the past few years we have seen a convergence of two largescale trends: Big Data and Big Compute. The resulting combination of large amounts of data and abundant CPU (and GPU) cycles has brought to the forefront and highlighted the power of neural network techniques and approaches that were once thought to be too impractical.
Deep Learning, as this new wave of interest has come to be known, has made impressive and unprecedented progress on applications as diverse as Natural Language Processing, Machine Translation, Computer Vision, Robotics, etc. In this lecture, students will learn, in a handson way, the theoretical foundations and principal ideas underlying this burgeoning field. The code structure of the implementations provided is meant to closely resemble the way the state of the art deep learning libraries Keras is structured so that by the end of the course, students will be prepared to dive deeper into the deep learning applications of their choice.
What you'll learnand how you can apply it
 Linear regression
 Logistic regression
 Perceptrons and neurons
 Back propagation
 Autoencoders
 Training deep networks
This training course is for you because...
 You are a data scientist who is interested in mastering the concepts and ideas behind neural networks and deep learning.
 You may have either no previous experience in neural networks or machine learning, and want to take the first grounded steps, or you may have previous experience in using neural network libraries such as Keras or Tensorflow, and wish to get a greater understanding of what’s going on “under the hood.”
Prerequisites
Attendees should have experience with:  Basic Python  Numpy  Matplotlib  Jupyter
Course Setup
 Scientific Python distribution like Anaconda
Recommended Preparation
If you need to brush up on Python:  (video) Python Programming Language LiveLessons by David Beazley:  (video) Modern Python LiveLessons: Big Ideas and Little Code in Python by Raymond Hettinger
Recommended Followup
After you complete the Deep Learning from Scratch Live Online Training class, you may find the following resources helpful:  (live online training) Deep Learning for NLP by Jon Krohn (search the O'Reilly Learning Platform for an upcoming class)  (video) Deep Reinforcement Learning and GANs: Advanced Topics in Deep Learning  (video) Understanding Convolutional Neural Networks  (book) Learn Keras for Deep Neural Networks: A FastTrack Approach to Modern Deep Learning with Python  (video) Natural Language Processing LiveLessons by Bruno Gonçalves
Stay connected with Bruno and uptodate on the world of data, science, and machine learning at https://data4sci.com/newsletter.
About your instructor

Bruno Gonçalves is currently a Senior Data Scientist working at the intersection of Data Science and Finance. Previously, he was a Data Science fellow at NYU's Center for Data Science while on leave from a tenured faculty position at AixMarseille Université. Since completing his PhD in the Physics of Complex Systems in 2008 he has been pursuing the use of Data Science and Machine Learning to study Human Behavior. Using large datasets from Twitter, Wikipedia, web access logs, and Yahoo! Meme he studied how we can observe both large scale and individual human behavior in an obtrusive and widespread manner. The main applications have been to the study of Computational Linguistics, Information Diffusion, Behavioral Change and Epidemic Spreading. In 2015 he was awarded the Complex Systems Society's 2015 Junior Scientific Award for "outstanding contributions in Complex Systems Science" and in 2018 is was named a Science Fellow of the Institute for Scientific Interchange in Turin, Italy.
Schedule
The timeframes are only estimates and may vary according to how the class is progressing
Segment 1  Regression (30 min)
 Understand the different types of Machine Learning
 Define Supervised Learning and Regression
 Visualize Linear Regression
 Implement Gradient Descent
 Use Linear Regression
Break (10 min)
Segment 2  Classification (40 min)
 Define Classification
 Visualize Logistic Regression
 Learning Procedure
 Implement Logistic Regression
 Understand Classification evaluation
Break (10min)
Segment 3 – Data Preparation (20 min)
 Visualize decision boundaries
 Use Data Normalization
 Understand Overfitting
 Define the Bias Variance Tradeoff
Break (10min)
Segment 4  Neural Networks (30 min)
 Understand how the brain works
 Understand Perceptrons and Forward Propagation
 Define Activation Functions
 Understand Back Propagation
Break (10 min)
Segment 5 – Recognizing Numbers (50 min)
 Understand the MNIST Dataset
 Understand Data Preparation
 Implement Back Propagation
 Understand the effect of the Learning Rate
 Generalize the Code
Break (10 min)
Segment 6 – Advanced network applications (50 min)
 Understand unsupervised Learning
 Implement an AutoEncoder
 Understand Recurrent Neural Networks
 Understand Convolutional Neural Networks
 Explore the Learning vs Memorization Tradeoff