Monthly Subscription Starting at AED 99 + VAT

Introduction to Deep Learning
  • Level Professional
  • Duration 60 hours
  • Course by University of Colorado Boulder
  • Offered by

About

Deep Learning is the go-to technique for many applications, from natural language processing to biomedical. Deep learning can handle many different types of data such as images, texts, voice/sound, graphs and so on. This course will cover the basics of DL including how to build and train multilayer perceptron, convolutional neural networks (CNNs), recurrent neural networks (RNNs), autoencoders (AE) and generative adversarial networks (GANs). The course includes several hands-on projects, including cancer detection with CNNs, RNNs on disaster tweets, and generating dog images with GANs. Prior coding or scripting knowledge is required. We will be utilizing Python extensively throughout the course. We recommend taking the two previous courses in the specialization, Introduction to Machine Learning: Supervised Learning and Unsupervised Algorithms in Machine Learning, but they are not required. College-level math skills, including Calculus and Linear Algebra, are needed. Some parts of the class will be relatively math intensive. This course can be taken for academic credit as part of CU Boulder’s MS in Data Science or MS in Computer Science degrees offered on the Coursera platform. These fully accredited graduate degrees offer targeted courses, short 8-week sessions, and pay-as-you-go tuition. Admission is based on performance in three preliminary courses, not academic history. CU degrees on Coursera are ideal for recent graduates or working professionals. Learn more: MS in Data Science: https://www.coursera.org/degrees/master-of-science-data-science-boulder MS in Computer Science: https://coursera.org/degrees/ms-computer-science-boulder Course logo image by Ryan Wallace on Unsplash.

Modules

Introduction

    • 1 Videos
    • 4 Readings
    • 1 Discussion
Show info about module content

1 Discussions

  • Introduce Yourself

1 Videos

  • Introduction to Deep Learning

4 Readings

  • Earn Academic Credit for your Work!
  • Course Support
  • Pre-Requisite Course Knowledge
  • Course Readings

Programming Assignments

    • 1 Readings
Show info about module content

1 Readings

  • Things of Note for Programming Assignments

Slide Decks

    • 2 Readings
Show info about module content

2 Readings

  • Module 1 Slides
  • Recommended Readings

Introduction to Deep Learning, Multi-Layer Perceptron

    • 3 Videos
    • 1 Quiz
Show info about module content

3 Videos

  • Perceptron Definition
  • Perceptron Training
  • MLP (multi-layer perceptron)

1 Quiz

  • Week 1 Lesson 1 Quiz

Back Propagation

    • 2 Videos
    • 1 Quiz
Show info about module content

2 Videos

  • Back Propagation Intro & Chain Rule
  • Computation Graph

1 Quiz

  • Week 1 Lesson 2 Quiz

Assessments

    • 1 PeerReview
    • 1 Programming
Show info about module content

1 Programming

  • Week 1: Neural Networks

1 Peer Review

  • Week 1: Neural Networks

Slide Decks

    • 2 Readings
Show info about module content

2 Readings

  • Module 2 Slides
  • Recommended Readings

Optimization

    • 4 Videos
Show info about module content

4 Videos

  • Stochastic Gradient Descent (SGD)
  • Tips to improve SGD
  • Advanced Optimization Methods
  • Tips for training neural networks

Using Keras

    • 2 Videos
Show info about module content

2 Videos

  • GPUs in Deep Learning
  • Introduction to Keras Library

Assessments

    • 1 Quiz
    • 1 PeerReview
    • 1 Lab
Show info about module content

1 Peer Review

  • Week 2: Stochastic Gradient Descent

1 Labs

  • Week 2: Stochastic Gradient Descent

1 Quiz

  • Week 2 Quiz

Slide Decks

    • 2 Readings
Show info about module content

2 Readings

  • Module 3 Slides
  • Recommended Readings

Convolutional Neural Networks

    • 6 Videos
Show info about module content

6 Videos

  • MLP Review
  • Convolution Layer
  • Convolution Design Parameters
  • Why is convolution useful?
  • Pooling Layer
  • Multiple Convolution Layer

CNN Architectures

    • 5 Videos
Show info about module content

5 Videos

  • CNN Review
  • Factors that made Deep Learning popular
  • Three basic CNN architectures
  • Training Tips
  • Transfer Learning

Assessments

    • 1 Quiz
    • 1 PeerReview
Show info about module content

1 Peer Review

  • Week 3: CNN Cancer Detection Kaggle Mini-Project

1 Quiz

  • Week 3 Quiz

Slide Decks

    • 2 Readings
Show info about module content

2 Readings

  • Module 4 Slides
  • Recommended Readings

Recurrent Neural Network Introduction

    • 1 Videos
Show info about module content

1 Videos

  • Introduction to RNN

Training and Optimizing RNNs

    • 2 Videos
Show info about module content

2 Videos

  • Training RNN
  • Limitations of vanilla_RNN

Special Types of RNNs

    • 1 Videos
Show info about module content

1 Videos

  • LSTM and GRU

Assessments

    • 1 PeerReview
Show info about module content

1 Peer Review

  • Week 4: NLP Disaster Tweets Kaggle Mini-Project

Slide Decks

    • 1 Readings
Show info about module content

1 Readings

  • Module 5 Slides

Introduction to Unsupervised Deep Learning

    • 1 Videos
Show info about module content

1 Videos

  • Overview of Unsupervised Approaches in Deep Learning

Autoencoders

    • 2 Videos
Show info about module content

2 Videos

  • Autoencoders
  • Variational autoencoders

Generative Adversarial Networks (GANs)

    • 1 Videos
    • 1 Readings
Show info about module content

1 Videos

  • Generative Adversarial Networks

1 Readings

  • Recommended Readings About GANs

Assessments

    • 1 PeerReview
Show info about module content

1 Peer Review

  • Week 5: GANs

Auto Summary

Explore the essentials of Deep Learning with this comprehensive course designed for Data Science and AI enthusiasts. Led by expert instructors, this professional-level course delves into building and training multilayer perceptrons, CNNs, RNNs, autoencoders, and GANs using Python. With a strong emphasis on hands-on projects like cancer detection and disaster tweet analysis, it requires prior coding knowledge and college-level math skills. Ideal for recent graduates or professionals, it offers flexible subscription options and contributes to CU Boulder’s MS degrees in Data Science or Computer Science. Duration: 3600 minutes.

Geena Kim
Instructor

Geena Kim