Duration
3 days
What you'll learn
- Artificial Neural Networks (ANNs) / Deep Neural Networks (DNNs)
- Predict Stock Returns
- Time Series Forecasting
- Computer Vision
- How to build a Deep Reinforcement Learning Stock Trading Bot
- GANs (Generative Adversarial Networks)
- Recommender Systems
- Image Recognition
- Convolutional Neural Networks (CNNs)
- Recurrent Neural Networks (RNNs)
- Use Tensorflow Serving to serve your model using a RESTful API
- Use Tensorflow Lite to export your model for mobile (Android, iOS) and embedded devices
- Use Tensorflow's Distribution Strategies to parallelize learning
- Low-level Tensorflow, gradient tape, and how to build your own custom models
- Natural Language Processing (NLP) with Deep Learning
- Demonstrate Moore's Law using Code
- Transfer Learning to create state-of-the-art image classifiers
DAY 1
9:00am - 10:30am
Google Colab
- Tensorflow 2.0 in Google Colab
- Uploading your own data to Google Colab
- Where can I learn about Numpy, Scipy, Matplotlib, Pandas, and Scikit-Learn?
10:30am - 10:45am Morning Break
10:45am - 12:30pm
Machine Learning and Neurons
- What is Machine Learning?
- Code Preparation (Classification Theory)
- Beginner's Code Preamble
- Classification Notebook
- Code Preparation (Regression Theory)
- Regression Notebook
- The Neuron
- How does a model "learn"?
- Making Predictions
- Saving and Loading a Model
- Why Keras?
- Suggestion Box
12:30pm - 1:30pm Lunch Break
1:30pm - 3:30pm
Feedforward Artificial Neural Networks
- Artificial Neural Networks Section Introduction
- Forward Propagation
- The Geometrical Picture
- Activation Functions
- Multiclass Classification
- How to Represent Images
- Code Preparation (ANN)
- ANN for Image Classification
- ANN for Regression
3:30pm - 3:45pm Afternoon Break
3:45pm - 5:00pm
Convolutional Neural Networks
- What is Convolution?
- Convolution on Color Images
- CNN Architecture
- CNN Code Preparation
- CNN for Fashion MNIST
- CNN for CIFAR-10
- Data Augmentation
- Batch Normalization
- Improving CIFAR-10 Results
DAY 2
9:00am - 10:30am
Recurrent Neural Networks, Time Series, and Sequence Data
- Sequence Data
- Forecasting
- Autoregressive Linear Model for Time Series Prediction
- Proof that the Linear Model Works
- Recurrent Neural Networks
- RNN Code Preparation
- RNN for Time Series Prediction
- Paying Attention to Shapes
- GRU and LSTM (pt 1)
- GRU and LSTM (pt 2)
- A More Challenging Sequence
- Demo of the Long Distance Problem
- RNN for Image Classification (Theory)
- RNN for Image Classification (Code)
- Stock Return Predictions using LSTMs
- Other Ways to Forecast
10:30am - 10:45am Morning Break
10:45am - 12:30pm
Natural Language Processing (NLP)
- Embeddings
- Code Preparation (NLP)
- Text Preprocessing
- Text Classification with LSTMs
- CNNs for Text
- Text Classification with CNNs
12:30pm - 1:30pm Lunch Break
1:30pm - 3:30pm
Recommender Systems
- Recommender Systems with Deep Learning Theory
- Recommender Systems with Deep Learning Code
Transfer Learning for Computer Vision
- Transfer Learning Theory
- Some Pre-trained Models (VGG, ResNet, Inception, MobileNet)
- Large Datasets and Data Generators
- 2 Approaches to Transfer Learning
- Transfer Learning Code
3:30pm - 3:45pm Afternoon Break
3:45pm - 5:00pm
GAN (Generative Adversarial Networks)
- GAN Theory
- GAN Code
DAY 3
9:00am - 10:30am
Deep Reinforcement Learning
- Deep Reinforcement Learning Section Introduction
- Elements of a Reinforcement Learning Problem
- States, Actions, Rewards, Policies
- Markov Decision Processes (MDPs)
- The Return
- Value Functions and the Bellman Equation
- What does it mean to “learn”?
- Solving the Bellman Equation with Reinforcement Learning
- Epsilon-Greedy
- Q-Learning
- Deep Q-Learning / DQN
- How to Learn Reinforcement Learning
10:30am - 10:45am Morning Break
10:45am - 12:30pm
Stock Trading Project with Deep Reinforcement Learning
- Reinforcement Learning Stock Trader Introduction
- Data and Environment
- Replay Buffer
- Program Design and Layout
- Code
- Reinforcement Learning Stock Trader Discussion
- Help! Why is the code slower on my machine?
12:30pm - 1:30pm Lunch Break
1:30pm - 3:30pm
Advanced Tensorflow Usage
- What is a Web Service?
- Tensorflow Serving
- Tensorflow Lite (TFLite)
- Why is Google the King of Distributed Computing?
- Training with Distributed Strategies
- Using the TPU
Low-Level Tensorflow
- Differences Between Tensorflow 1.x and Tensorflow 2.x
- Constants and Basic Computation
- Variables and Gradient Tape
- Build Your Own Custom Model
3:30pm - 3:45pm Afternoon Break
3:45pm - 5:00pm
In-Depth: Loss Function
- Mean Squared Error
- Binary Cross Entropy
- Categorical Cross Entropy
In-Depth: Gradient Descent
- Gradient Descent
- Stochastic Gradient Descent
- Momentum
- Variable and Adaptive Learning Rates
- Adam
Programme scope, delivery arrangements and suitability are confirmed during enquiry.