In this course, you learn the essentials of Deep Learning. We start with a brief introduction and illustrate how to set up your software environment. We then review the foundations of artificial neural networks such as the perceptron and multilayer perceptron (MLP) networks. Next, we elaborate on convolutional neural networks illustrated with various examples. We then discuss representational learning and embeddings. Recurrent neural networks are also covered again extensively illustrated with examples. This is followed by a discussion on generative adversarial networks. The course concludes by discussing reinforcement learning.
The course provides a sound mix of both theoretical and technical insights, as well as practical implementation details. These are illustrated by several real-life case studies and examples using Keras and TensorFlow.
The course features 28 Jupyter notebooks containing hands-on examples. A Python tutorial is also provided.
The course features more than 4 hours of video lectures, various multiple choice questions, and lots of references to background literature. A certificate signed by the instructors is provided upon successful completion.
We can also come and teach this course on-site in classroom format. If interested, please mail us at: Bart@BlueCourses.com.
Price
The enrollment fee for this course is EUR 100 (VAT excl.) per participant. Payments are securely handled by PayPal. If you are a company in the European Union, then we can apply VAT reverse charge. For this, please mail your VAT number to Bart@BlueCourses.com. Part of our course revenue is used towards funding organizations involvement in protecting and cleaning our oceans. See our about page to learn more about our mission statement.
Requirements
Before subscribing to this course, you should have a basic understanding of descriptive statistics (e.g., mean, median, standard deviation, histograms, scatter plots, etc.) and inference (e.g., confidence intervals, hypothesis testing). You should also have followed and completed our Machine Learning Essentials course.
Course Outline
Chapter 1: Introduction
About
From if-then rules to deep learning
Comparison
A brief history of deep learning
What will be covered
Chapter 2: Getting ready for deep learning
Software
Setting up your environment
Chapter 3: Foundations of artificial neural networks
The perceptron
Concept
Activation and transfer functions
Bias
Training a perceptron
A simple iterative approach
☞ A simple perceptron in Python
Gradient descent
The XOR problem
Multilayer perceptron (MLP) networks
Backpropagation
Automatic differentiation
☞ Automatic differentiation in TensorFlow
Summary so far
☞ Handwritten digits recognition with an MLP
Further aspects
Activation functions
ReLU
Initialization
☞ The importance of initialization
Loss functions
Stochastic gradient descent
Backpropagation alternatives
Optimizers
Learning rate
Preventing overfitting
Hyperparameter optimization
Quiz
Chapter 4: Convolutional neural networks
The convolutional architecture
Concept
Filters and pooling
☞ Handwritten digits recognition with a CNN
Best practices
Dropout
Batch normalization
Data augmentation
☞ Colored image classification with a CNN
Opening the black box
☞ Interpretability examples with a CNN
Further aspects
Transfer learning
☞ Transfer learning with a CNN
Variants
☞ Locating objects with a CNN
Capsule networks
Adversarial attacks
Use cases
Deep dream
☞ Deep dreaming example
Artistic style transfer
☞ Artistic style transfer example
Quiz
Chapter 5: Representational learning
Embeddings in text
Concept
Word embeddings
word2vec
☞ Building a word2vec model
Use cases
Generalizing embeddings
Further aspects
Variants
☞ Graph embeddings example
Software
Categorical embeddings
☞ Featurization with categorical embeddings
Auto-encoders
☞ Anomaly detection with auto-encoders
☞ Image denoising with auto-encoders
Quiz
Chapter 6: Recurrent neural networks
The recurrent architecture
Concept
☞ An RNN from scratch
Common RNNs
☞ Text classification with an RNN
☞ Text generation with an RNN
Further aspects
Variants
Attention and memory
☞ Text classification with attention
Time series
☞ Time series forecasting with an LSTM
Revisiting the CNN
☞ Text classification with a CNN
Quiz
Chapter 7: Generative adversarial networks
The generative adversarial architecture
Concept
☞ Generating digits with a GAN
Challenges
Best practices
☞ Generating digits with a GAN, revisited
Further aspects
Variants
Use cases
Quiz
Chapter 8: Reinforcement learning
Reinforcement learning
Concept
Q learning
☞ Q learning example
Deep Q learning
☞ Deep Q learning example
Further aspects
Variants
☞ Double deep Q learning example
Software
Challenges
Quiz
Chapter 9: Conclusions
Course Staff
Prof. dr. Seppe vanden Broucke
Seppe vanden Broucke is an assistant professor at the department of Business Informatics at UGent (Belgium) and is a lecturer at KU Leuven (Belgium). His research interests include business data mining and analytics, machine learning, process management and process mining. His work has been published in well-known international journals and presented at top conferences. He is also author of the books Beginning Java Programming (Wiley, 2015) and Principles of Database Management (Cambridge University Press, 2018). Seppe's teaching includes Advanced Analytics, Big Data and Information Management courses. He also frequently teaches for industry and business audiences. See seppe.net for further details.
