In this course you will learn the fundamentals of Deep Learning primarily through a series of hands on exercises guided by the instructor. Students will learn about the foundational underpinnings of machine learning and deep learning as well as how to put that knowledge to the test with practical exercises. Identify and frame problems that can be solved by deep learning
Choose the right techniques to the problems
Understand key deep learning concepts and how deep learning models work
Build deep neural nets for classification on images as well as structured data using the Keras.
Build convolutional neural networks for image classification and segmentation using the Keras.
Describe reinforcement learning and Implement reinforcement learning to play games.
The course takes unique project focused approach to teach you deep learning by building deep learning models. The instructor will walk you through a series of curated projects, and explain the key concepts as they arise. Students will learn the theory and how these models work under the hood while writing code, and building neural networks.
The course will balance learning theory, working on projects, and hearing from guest speakers who are industry practitioners in the field.
Students who take this course will be able to:
- Session 1: May. 14th Tue 10am-12pm PST
- Session 2: May. 16th Thu 10am-12pm PST
- Session 3: May. 21st Tue 10am-12pm PST
- Session 4: May. 23rd Thu 10am-12pm PST
- Session 5: May. 28th Tue 10am-12pm PST
- Session 6: May. 30th Thu 10am-12pm PST
- Session 7: Jun. 4th Tue 10am-12pm PST
- Session 8: Jun. 6th Thu 10am-12pm PST
- 16 hours/ 8 sessions
- 10 lectures / 12 hands-on code labs
- Live Sessions, Real time interactions
- Watch sessions replay anywhere any time
- Forum supports to projects and homeworks
Check the content tab for full course outlines.
WHO SHOULD LEARN:
Developers, data scientists, students who want to get started on building deep learning projects or applications.
Familiarity with Python, or willingness to learn it quickly
Basic familiarity with statistics and probability theory is a plus, but not required
Comfort with the command line a plus
We believe the course will be helpful for you like majority of other attendees. Even if you can find it not in your expectation level you will get full refund upon request before the first session ends (May 14th 12pm PST).
If you miss the live session or want to learn again, you can watch recorded sessions any time, along with interactive learning tools, slides, course notes
Certificate of completing course is available upon request
Job referral service is available, contact us for details
Financial aid is available, contact us for applications
Module 1: Machine Learning & Neural Network Fundamentals
- Deep learning applications, key concepts and terminology
- Neural network architecture and theory
- Code lab environment setup
- Code lab 1: build first deep learning model to classify handwritten digits
Module 2: Improving Deep Neural Networks
- Identify tasks that are well and ill suited to deep learning
- Underfitting and overfitting, Regularization tactics
- Feature engineering
- Optimizers and training parameters
- Code Lab 2: Explore the impact different neural network architectures
- Code Lab 3: Explore the impact of different optimizers, dropout, and regularization tactics
Module 3: Data Cleaning and Preprocessing
- Define and identify common problems with training data
- Describe and apply tactics for improving data quality and improve network performance
- Evaluate the appropriateness of applying said tactics.
- Code Lab 4: Clean up a messy dataset
- Code Lab 5: Improve a dataset with synthetic data and augmentation
Module 4: Convolutional neural networks for classification and segmentation
- Identify tasks for which CNNs are well suited
- Compare and contrast classification with segmentation
- Build CNNs from scratch using Keras and evaluate their performance
- Code Lab 6: Build your first CNN to classify images
- Code Lab 7: Build CNN model to identify items within an image
Module 5: Continue with CNN 2
- Transfer learning and identify examples of situations where it might help
- Import well known CNN architectures and leverage transfer learning using Keras
- Code Lab 8: Identify flower species project
- Code Lab 9: Import pre-trained CNN’s and apply Transfer Learning have classify a different dataset
- Tech talk by guest speaker
Module 6: Reinforcement learning
- Identify situations where reinforcement learning can be applied
- Build a policy based reinforcement learning agent and train it on an OpenAI Gym environment
- Code Lab 10: Implement Q-Learning to play simple games, such as Cart Pole and Mountain Car
Module 7: Deep reinforcement learning
- Replace the Q-function with a neural network to implement deep-q learning
- Build a simple deep q-learning agent using OpenAI’s Gym and and Keras
- Code Lab 11: Reimplement Q-learning with a deep neural network to play the same simple games
Module 8: continue with Deep Reinforcement Learning 2
- Implement experience replay to improve Deep Reinforcement Learning
- Use a CNN to process the raw pixel data as the state for a Q-Learning agent
- Code Lab 12: Improve the Q-Learning agent with experience replay
- Code Lab 13: Use a CNN to process the state with Q-learning
- Tech talk by guest Speaker
Tyler (Lead Instructor) is an educator, technologist, programmer, and all around curious human. He holds a bachelor’s degree in computer science, and is now focused on technology education and outreach.
Suqiang Song (Guest Speaker)
Director of AI platform at Mastercard, focuses on appling machine learning and deep learning tech to product and service, builds Data Engineering and AI shared services at the company.