Deep Learning

Deep Learning

Deep Learning

Intermediate

Via analogy to biological neurons and human perception, this course is an introduction to artificial neural networks that brings high-level theory to life with interactive labs featuring TensorFlow, the most popular open-source Deep Learning library. Essential theory will be covered in a manner that provides students with an intuitive understanding of Deep Learning's underlying foundations. Paired with hands-on code run-throughs in Jupyter notebooks as well as strategies 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 the major contemporary families: Convolutional Nets for machine vision; Long Short-Term Memory Recurrent Nets for natural language processing and time series analysis; Generative Adversarial Networks for producing realistic images; and Reinforcement Learning for playing video games.

Course Overview
Intermediate

Via analogy to biological neurons and human perception, this course is an introduction to artificial neural networks that brings high-level theory to life with interactive labs featuring TensorFlow, the most popular open-source Deep Learning library. Essential theory will be covered in a manner that provides students with an intuitive understanding of Deep Learning's underlying foundations. Paired with hands-on code run-throughs in Jupyter notebooks as well as strategies 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 the major contemporary families: Convolutional Nets for machine vision; Long Short-Term Memory Recurrent Nets for natural language processing and time series analysis; Generative Adversarial Networks for producing realistic images; and Reinforcement Learning for playing video games.

July Session
$2990.00
July Session
Jul 21 - Aug 18, 2018, 10:00am-4:00pm
October Session
$2990.00
Early bird pricing
$2840.50
October Session
Oct 20 - Dec 1, 2018, 10:00am-4:00pm

Date and Time

July Session

Jul 21 - Aug 18, 2018, 10:00am-4:00pm
Day 1: July 21, 2018
Day 2: July 28, 2018
Day 3: August 4, 2018
Day 4: August 11, 2018
Day 5: August 18, 2018
$2990.00
Add to Cart

October Session Early-bird Pricing!

Oct 20 - Dec 1, 2018, 10:00am-4:00pm
Day 1: October 20, 2018
Day 2: October 27, 2018
Day 3: November 3, 2018
Day 4: November 17, 2018
Day 5: December 1, 2018
$2990.00$2840.50
Add to Cart

Instructors

Jon Krohn
Jon Krohn
Jon Krohn is Chief Data Scientist at the machine-learning startup untapt. He presents an acclaimed series of tutorials on artificial neural networks, including Deep Learning with TensorFlow LiveLessons. Jon holds a doctorate in neuroscience from Oxford University and has been publishing on machine learning in leading academic journals since 2010. His forthcoming book, Deep Learning Illustrated, is being published on Pearson's Addison-Wesley imprint and will be distributed in 2018.

Product Description


Overview

 

Facilitated by the intersection of inexpensive computing power, unprecedently large data sets, and clever computational statistics advances, Deep Learning algorithms are driving an Artificial Intelligence revolution. Deep Learning has emerged as uniquely influential across a broad range of the statistical domain, including classification (e.g., visual recognition, sentiment analysis), prediction (e.g., stock markets, health outcomes) and generation (e.g., creating images, composing music). In the past few years, Deep Neural Networks have made their way into countless everyday applications, including Tesla’s Autopilot, Siri’s voice recognition, Facebook’s face identification, and hundreds of products at Google such as Inbox with its suggested replies. Indeed, Deep Learning algorithms have exceeded human performance on previously intractable computational problems like language translation, object detection, and the game of Go.

Via analogy to biological neurons and human perception, this course is an introduction to artificial neural networks that brings high-level theory to life with interactive labs featuring TensorFlow, the most popular open-source Deep Learning library. Essential theory will be covered in a manner that provides students with an intuitive understanding of Deep Learning’s underlying foundations. Paired with hands-on code run-throughs in Jupyter notebooks as well as strategies 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 the major contemporary families: Convolutional Nets for machine vision; Long Short-Term Memory Recurrent Nets for natural language processing and time series analysis; Generative Adversarial Networks for producing realistic images; and Reinforcement Learning for playing video games.


Details


Instructor Interview


Jon Krohn, Instructor for Deep Learning course at NYC Data Science Academy on Vimeo.


Goals

 

This is a “short course” of five weeks, with six hours of class per week. Classes will be given in a lab setting, with hands-on exercises mixed with lectures. Students should bring a laptop to class. You will have the option of creating and completing your own major Deep Learning project over the duration of the program.

Who Is This Course For?

 

This course is perfect for software engineers, data scientists, analysts, and statisticians with an interest in Deep Learning. No previous knowledge of Deep Learning is assumed. Previous experience with statistics or machine learning is not necessary, but will be an asset if you have it. Code examples are provided in Python, so familiarity with it or another object-oriented programming language would be helpful.

Prerequisites

 

It will be challenging to follow along through the code demos and exercises without some experience in:

  • object-oriented programming, ideally Python (introductory course: https://nycdatascience.com/courses/introductory-python/)
  • simple shell commands, e.g., in Bash (tutorial of the fundamentals: https://learnpythonthehardway.org/book/appendixa.html)

Outcomes

 

By the end of the course, you will be able to:
  • build Deep Learning models in TensorFlow and Keras
  • interpret the results of Deep Learning models
  • troubleshoot and improve Deep Learning models
  • understand the language and fundamentals of artificial neural networks
  • build your own Deep Learning project

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.

 

Syllabus

Unit 1: The Unreasonable Effectiveness of Deep Learning

  • An Introduction to Neural Networks and Deep Learning
  • Course Survey
  • Interactive Visualization of an Artificial Neural Network
  • Hardware Options for Deep Learning, including How to Build a Deep Learning Server
  • Running a TensorFlow Jupyter Notebook within a Docker Container
  • A Shallow Artificial Neural Network

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 a Deep Neural Network
  • 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 Neural Network
  • TensorBoard and the Interpretation of Model Outputs

Unit 4: Machine Vision

  • Introduction to Convolutional Neural Networks for Visual Recognition
  • Classic ConvNet Architecture I: LeNet-5
  • Classic ConvNet Architecture II: AlexNet
  • Transfer Learning
  • The Families of Deep Neural Nets and their Applications
  • Your Deep Learning Project: Formulating

Unit 5: TensorFlow

  • Reviewing Content and Take-Home Exercises
  • Comparison of the Leading Deep Learning Libraries
  • TensorFlow Graphs
  • Neurons in TensorFlow
  • Fitting Models in TensorFlow

Unit 6: Deep Learning with TensorFlow

  • Deep Dense Nets in TensorFlow
  • Deep Convolutional Nets in TensorFlow
  • TensorBoard Best-Practices
  • Improving Model Performance
  • Tuning Hyperparameters
  • Your Deep Learning Project: Assessing

Unit 7: Natural Language Processing

  • Reviewing Content and Take-Home Exercises
  • Word Vectors: word2vec and Vector-Space Embedding
  • Recurrent Neural Networks
  • Long Short-Term Memory Units
  • Sentiment Analysis

Unit 8: Time Series Analysis

  • Machine Translation: Sequence-to-Sequence Models and Attention
  • Neural Network Architectures for Question-Answering
  • Forecasting with Financial Time Series Data
  • Your Deep Learning Project: Improving

Unit 9: Generative Adversarial Networks

  • Reviewing Content and Take-Home Exercises
  • Applications of GANs
  • Essential Theory of GANs
  • Implementations of GANs

Unit 10: Reinforcement Learning

  • Applications of Reinforcement Learning
  • OpenAI Gym
  • Essential Theory of Reinforcement Learning
  • Implementations of Reinforcement Learning
  • Jeanne Calment and Your Role in the AI Revolution

Follow-Up Session Three Weeks Later

  • Your Deep Learning Project: Presentation

Reviews

There are no reviews yet.

Instructors

Jon Krohn
Jon Krohn
Jon Krohn is Chief Data Scientist at the machine-learning startup untapt. He presents an acclaimed series of tutorials on artificial neural networks, including Deep Learning with TensorFlow LiveLessons. Jon holds a doctorate in neuroscience from Oxford University and has been publishing on machine learning in leading academic journals since 2010. His forthcoming book, Deep Learning Illustrated, is being published on Pearson's Addison-Wesley imprint and will be distributed in 2018.

Product Description


Overview

 

Facilitated by the intersection of inexpensive computing power, unprecedently large data sets, and clever computational statistics advances, Deep Learning algorithms are driving an Artificial Intelligence revolution. Deep Learning has emerged as uniquely influential across a broad range of the statistical domain, including classification (e.g., visual recognition, sentiment analysis), prediction (e.g., stock markets, health outcomes) and generation (e.g., creating images, composing music). In the past few years, Deep Neural Networks have made their way into countless everyday applications, including Tesla’s Autopilot, Siri’s voice recognition, Facebook’s face identification, and hundreds of products at Google such as Inbox with its suggested replies. Indeed, Deep Learning algorithms have exceeded human performance on previously intractable computational problems like language translation, object detection, and the game of Go.

Via analogy to biological neurons and human perception, this course is an introduction to artificial neural networks that brings high-level theory to life with interactive labs featuring TensorFlow, the most popular open-source Deep Learning library. Essential theory will be covered in a manner that provides students with an intuitive understanding of Deep Learning’s underlying foundations. Paired with hands-on code run-throughs in Jupyter notebooks as well as strategies 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 the major contemporary families: Convolutional Nets for machine vision; Long Short-Term Memory Recurrent Nets for natural language processing and time series analysis; Generative Adversarial Networks for producing realistic images; and Reinforcement Learning for playing video games.


Details


Instructor Interview


Jon Krohn, Instructor for Deep Learning course at NYC Data Science Academy on Vimeo.


Goals

 

This is a “short course” of five weeks, with six hours of class per week. Classes will be given in a lab setting, with hands-on exercises mixed with lectures. Students should bring a laptop to class. You will have the option of creating and completing your own major Deep Learning project over the duration of the program.

Who Is This Course For?

 

This course is perfect for software engineers, data scientists, analysts, and statisticians with an interest in Deep Learning. No previous knowledge of Deep Learning is assumed. Previous experience with statistics or machine learning is not necessary, but will be an asset if you have it. Code examples are provided in Python, so familiarity with it or another object-oriented programming language would be helpful.

Prerequisites

 

It will be challenging to follow along through the code demos and exercises without some experience in:

  • object-oriented programming, ideally Python (introductory course: https://nycdatascience.com/courses/introductory-python/)
  • simple shell commands, e.g., in Bash (tutorial of the fundamentals: https://learnpythonthehardway.org/book/appendixa.html)

Outcomes

 

By the end of the course, you will be able to:
  • build Deep Learning models in TensorFlow and Keras
  • interpret the results of Deep Learning models
  • troubleshoot and improve Deep Learning models
  • understand the language and fundamentals of artificial neural networks
  • build your own Deep Learning project

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.

 

Syllabus

Unit 1: The Unreasonable Effectiveness of Deep Learning

  • An Introduction to Neural Networks and Deep Learning
  • Course Survey
  • Interactive Visualization of an Artificial Neural Network
  • Hardware Options for Deep Learning, including How to Build a Deep Learning Server
  • Running a TensorFlow Jupyter Notebook within a Docker Container
  • A Shallow Artificial Neural Network

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 a Deep Neural Network
  • 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 Neural Network
  • TensorBoard and the Interpretation of Model Outputs

Unit 4: Machine Vision

  • Introduction to Convolutional Neural Networks for Visual Recognition
  • Classic ConvNet Architecture I: LeNet-5
  • Classic ConvNet Architecture II: AlexNet
  • Transfer Learning
  • The Families of Deep Neural Nets and their Applications
  • Your Deep Learning Project: Formulating

Unit 5: TensorFlow

  • Reviewing Content and Take-Home Exercises
  • Comparison of the Leading Deep Learning Libraries
  • TensorFlow Graphs
  • Neurons in TensorFlow
  • Fitting Models in TensorFlow

Unit 6: Deep Learning with TensorFlow

  • Deep Dense Nets in TensorFlow
  • Deep Convolutional Nets in TensorFlow
  • TensorBoard Best-Practices
  • Improving Model Performance
  • Tuning Hyperparameters
  • Your Deep Learning Project: Assessing

Unit 7: Natural Language Processing

  • Reviewing Content and Take-Home Exercises
  • Word Vectors: word2vec and Vector-Space Embedding
  • Recurrent Neural Networks
  • Long Short-Term Memory Units
  • Sentiment Analysis

Unit 8: Time Series Analysis

  • Machine Translation: Sequence-to-Sequence Models and Attention
  • Neural Network Architectures for Question-Answering
  • Forecasting with Financial Time Series Data
  • Your Deep Learning Project: Improving

Unit 9: Generative Adversarial Networks

  • Reviewing Content and Take-Home Exercises
  • Applications of GANs
  • Essential Theory of GANs
  • Implementations of GANs

Unit 10: Reinforcement Learning

  • Applications of Reinforcement Learning
  • OpenAI Gym
  • Essential Theory of Reinforcement Learning
  • Implementations of Reinforcement Learning
  • Jeanne Calment and Your Role in the AI Revolution

Follow-Up Session Three Weeks Later

  • Your Deep Learning Project: Presentation

Reviews

There are no reviews yet.

Testimonials View All Student Testimonials

Richard Sheng, Co-Founder & CEO
Richard Sheng, Co-Founder & CEO
at
QuantumViz

"Highly Recommend Jon Krohn's Deep Learning Course"

Going into the course, I was slightly afraid that I would get lost in the mathematical concepts, and may not have the necessary technical know-how. Turns out I actually had a ton of fun with this class. Jon's class preparation goes beyond any educator I have worked with. He is able to illustrate the complex concepts with super-easy-to-understand visulizations and/or videos. When it came to application, he walked us through, line-by-line, all the code, and incrementally built up the complexity. Honestly, I can't believe we were able to cover convolutional models, recurrent models, generative adversarial networks, and deep reinforcement learning in such a short time. There was ample amount of sample code in Jupyter Notebooks to follow. Aside from that, Jon was just super nice guy and very humble. The course is beneficial to those that just want to learn in more detail how Artificial Intelligence can be applied, and also those that are more senior data scientists that want to add Deep Learning techniques to their tool-belt. My only recommendation for the school is that it would have been nicer for a cloud environment to be set up for us, or to have very specific instructions on how we can do so. It turned out to be a great learning experience anyway, but for a non-technical person, it was slightly daunting at first.
Khanan Grauer
Khanan Grauer

" Deep learning is an amazing class"

I took the class with Jon Krohn and could not be more pleased. Jon has a rare ability to take a complicated subject and reduce it to its fundamental elements. Instead of approaching the problems with math alone, Jon spends time crafting examples and analogies to make sure students understand the actual building blocks conceptually. That produces an epiphanic experience where we were able to visualize what is happening behind the scenes. The concepts I’ve learned in this class is something I plan to apply to real-world problems and therefore highly recommend this class to anyone who wants to learn about this field.
Michael Roman
Michael Roman

"This Deep Learning Course Was a Joy"

I recently graduated from Jon's Deep Learning course at the New York Data Science Academy and was a big fan. I think the course did a great job of introducing students to the deep learning landscape, helping us understand what makes deep learning techniques excel at a wide range of tasks and then diving into the code (Keras, TensorFlow) to show us how to spin up various networks (NN Regressors, NN Classifiers, Convolutional NN, RNN's, Reinforcement Learning networks, GANs). Jon is a PHD neuroscientist and one thing I particularly enjoyed about the course was that Jon drew upon his background to connect the artificial neural network content with its biological inspiration. To highlight an example, he weaves in the Cambrian Explosion and Hubel & Wiesel's breakthrough experiment on vision in cats to provide context and color on the emergence of complex biological vision systems on earth, its role in the explosion in speciation that occurred ~540 million years ago, and how in the (super recent, relatively) 1950's the scientific community finally began to understand the neural basis for visual perception. It was breakthroughs in scientific understanding like these that motivate certain machine vision architectures we explore in the course. It felt, at many moments, like really mind-bending stuff. Students are encouraged to complete a deep learning capstone project for the course and there were plenty of opportunities to get valuable feedback and mentorship when we got stuck, which was great. This course is probably best suited for folks with some background in coding and a familiarity with foundational machine learning concepts. Overall, it was time and money well spent.
read more
Mahipal S, Associate Director of Development
Mahipal S, Associate Director of Development
at
KPMG
I attended the Deep Learning course at the NY Data Science Academy that was taught by Jon Krohn during October 2017 - December 2017. Overall it was exactly what I hoped it would be. It gave me a strong foundation of all the core deep learning concepts. The class was hosted on every other Saturday which allowed enough time to fully explore a particular topic between classes. Jon made a particular effort to keep the material simple and explained the concepts intuitively rather than with complicated math. Jon has great understanding of the content and is well prepared for each lesson. I thoroughly enjoyed the class and it has motivated me to pivot my career into deep learning. I would recommend this class to anyone who is passionate about deep learning but don't know where to begin. It is also great for anyone who has worked with some but not all of the deep learning techniques.

Date and Time

July Session

Jul 21 - Aug 18, 2018, 10:00am-4:00pm
Day 1: July 21, 2018
Day 2: July 28, 2018
Day 3: August 4, 2018
Day 4: August 11, 2018
Day 5: August 18, 2018
$2990.00
Add to Cart

October Session Early-bird Pricing!

Oct 20 - Dec 1, 2018, 10:00am-4:00pm
Day 1: October 20, 2018
Day 2: October 27, 2018
Day 3: November 3, 2018
Day 4: November 17, 2018
Day 5: December 1, 2018
$2990.00$2840.50
Register before Aug 21st to take advantage of this price!
Add to Cart