From Beginner To Intermediate

Deep Learning with TensorFlow 2, Keras and PyTorch

A class for an introduction to artificial neural networks that brings high-level theory to life with interactive labs featuring TensorFlow, Keras, and PyTorch.

PD Deep Learning
Meet the instructors Alex Baransky
big data on wheels
Certificate Awarded
DP Deep Learning certificate
Best Data Science Bootcamp Switchup
4.89 / 5
(317 Reviews)
Best Data Science Bootcamp
5 Years Running
Course Report Rating
4.84 / 5
( 322 Reviews)
Best Data Science Bootcamp
5 Years Running

Deep Learning with TensorFlow 2, Keras and PyTorch

This course is an introduction to artificial neural networks that brings high-level theory to life with interactive labs featuring TensorFlow, Keras, and PyTorch — the leading Deep Learning libraries. Essential theory will be covered in a manner that provides students with a complete intuitive understanding of Deep Learning’s underlying foundations. Paired with hands-on code run-throughs in Jupyter notebooks as well as strategic advice for overcoming common pitfalls, this foundational knowledge will empower individuals with no previous understanding of neural networks to build production-ready Deep Learning applications across all of the contemporary families, including:

  • Convolutional Networks for machine vision
  • Long Short-Term Memory Recurrent Nets for natural language processing and time series analysis
  • Generative Adversarial Networks for producing jaw-dropping synthetic data
  • Reinforcement Learning for complex sequential decision-making
Unit 1: The Unreasonable Effectiveness of Deep Learning
  • An Introduction to Neural Networks and Deep Learning
  • Interactive Visualization of an Artificial Neural Network
  • Hardware Options for Deep Learning, including How to Build a Deep Learning Server
  • Running Jupyter Notebooks within a Docker Container
  • The Families of Deep Neural Nets and their Applications
  • A Shallow TensorFlow 2 Neural Network with Keras Layers
Unit 2: How Deep Learning Works
  • Essential Theory I: Neural Units
  • Interactive Visualization of Neural Units
  • Essential Theory II: Cost Functions, Gradient Descent, and Backpropagation
  • Interactive Visualization of Neural Networks
  • An Intermediate Neural Network
  • Data Sets for Deep Learning
  • Your Deep Learning Project: Ideating
Unit 3: Building and Training a Deep Learning Network
  • Review Content and Take-Home Exercises
  • Essential Theory III: Weight Initialization and Mini-Batches
  • Essential Theory IV: Unstable Gradients and Avoiding Overfitting
  • A Deep TensorFlow 2 Neural Network with Keras Layers
  • TensorBoard and the Interpretation of Model Outputs
Unit 4: Machine Vision
  • Introduction to Convolutional Neural Networks for Visual Recognition
  • Classic ConvNet Architectures: LeNet-5 and AlexNet
  • Object Detection
  • Image Segmentation
  • Transfer Learning
  • Your Deep Learning Project: Formulating
Unit 5: Natural Language Processing
  • Reviewing Content and Take-Home Exercises
  • Word Vectors: word2vec and Vector-Space Embedding
  • Recurrent Neural Networks
  • Long Short-Term Memory Units
  • Gated Recurrent Units
  • Classifying Documents: Sentiment Analysis
Unit 6: Time Series Analysis
  • Autoencoders: Encoder-Decoder Structures
  • Sequence-to-Sequence Models and Attention
  • Financial Forecasting
  • Hyperparameter Tuning
  • Non-Sequential Models
  • Your Deep Learning Project: Assessing
Unit 7: Advanced TensorFlow
  • Introducing TensorFlow Graphs
  • Representing Neurons as TensorFlow Graphs
  • Optimizing TensorFlow Graphs
  • Deep Learning with TensorFlow 1.x
  • Deep Learning with TensorFlow 2.x
Unit 8: PyTorch
  • Comparison of the Leading Deep Learning Libraries
  • Autodifferentiation
  • Sequential Deep Learning Models in PyTorch
  • Forward Propagation and Optimization in PyTorch
  • Model Validation in PyTorch
  • Your Deep Learning Project: Improving
Unit 9: Generative Adversarial Networks
  • GAN Applications
  • Essential GAN Theory
  • Simulating Artistic Creativity with a GAN
  • Resources for Deep Learning Self-Study
Unit 10: Reinforcement Learning
  • Applications of Reinforcement Learning
  • Reinforcement Learning Environments: OpenAI Gym
  • Essential Reinforcement Learning Theory
  • Deep Q-Learning Networks
  • Policy Gradients and the Actor-Critic Algorithm
  • Jeanne Calment and Your Role in the AI Revolution
  • Your Deep Learning Project: Presentation

* We do not offer this course at this moment. Please join our waiting list to be notified when it becomes available again.

ADD TO CART

Customer Reviews

I could not be more satisfied with my experience at NYC Data Science Academy. I met incredibly impressive and interesting people, learned more than I ever thought I could, made friends, and worked very hard. Within a few weeks after graduating, I was offered my first full-time job as a data engineer. (I do not come from a CS, math or stats background). NYC Data Science Academy is very successful at getting their students fluent in the tools and technologies of data science, and prepared for finding great jobs in the field. The bootcamp is exhilarating, and the people are truly the best. By the end, you will be ready to for a data science position, and you will have broadened your horizons.

Dean Goldman, Data Engineer, NYC Data Science Academy

 I had a Master in Business Analytics before joining NYC Data Science Academy, with a knowledge of programming and data science/machine learning. Though I knew how to make graphs and build models with R and Python, and knew some concepts learned from the online course on EDX and Coursera, this bootcamp was still truly helpful for me. My goal was to explore more deeply the big data techniques including Hadoop and Spark and get a chance to review data science and machine learning stuff in a systemic way. This bootcamp gave me almost everything I desired, with so many unexpected benefits. It was seriously life-changing for me. I achieved something that would otherwise never be possible had I just stuck with online courses. Read on for more detail. All the courses were well-designed. They covered everything I needed in my data science journey. Some might wonder why I chose to spend money on this bootcamp to learn something that seems available online. The reason for me was that I feel my time is quite valuable. 

Shuheng-Li, NYC Data Science Academy
View more customer reviews

Reasons to Enroll

Instructors

Our instructors are consistently highly rated by their students.  They not only know their subject cold, they are experts at teaching you.

Curriculum

Our curriculum is continuously updated to reflect the latest technology trends.

Technology

Learn on the latest technology.  When you complete this course, you will have a solid foundation in python and the use of the tools.

Jon Krohn
DATA SCIENCE INSTRUCTOR

Jon Krohn is the 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 LiveLessons in Safari, and teaches his Deep Learning curriculum at the NYC Data Science Academy. Jon holds a doctorate in neuroscience from Oxford University and has been publishing on machine learning in leading academic journals since 2010. He 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. His book, Deep Learning Illustrated, is being published by Pearson's Addison-Wesley in 2019 (https://www.deeplearningillustrated.com).

Jon Krohn, Deep Learning instructor

Your Certificate of Completion

Prerequisites

It would be challenging to follow along through the code demos and exercises without some experience in object-oriented programming, ideally Python (introductory course here). Students with experience in other languages (e.g., R) have, however, been very successful.

Certificate

Certificates are awarded at the end of the program at the satisfactory completion of the course. Students are evaluated on a pass/fail basis for their performance on the required homework and final project (where applicable). Students who complete 80% of the homework and attend a minimum of 85% of all classes are eligible for the certificate of completion.

Certificate of Completion

DP Deep Learning certificate

 

Simple Linear Regression

Module
Introduction and Regression
 
Instructor
Ryan Courtney
 
Description
NYC Data Science Academy's Instructor, Ryan Courtney, walks through a lecture on simple linear regression.
Enroll Now