This course gives you a strong foundation in deep learning using Keras and TensorFlow. The hands-on, workshop-style projects represent real-life scenarios, including collecting and cleaning up data, designing a model, training the model with data, and making predictions.
Prerequisites
- Basic programming experience in any language is needed. You will receive enough introduction to Python to complete this course.
- Knowledge of calculus and linear algebra is recommended but not necessary.
Outline
Workshop 1 - Tensorflow Basics
- Learn about Python language, Numpy, Pandas and Tensorflow.
Workshop 2 - Gradient Descent
- Learn how GD works and how machines learn using this technique.
Workshop 3 - Simple Linear Regression
- Perform linear regression in a very simple problem domain. The goal is to learn how linear regression works.
Workshop 4 - Ames, Iowa House Price Prediction Using Neural Network
- Learn the theory behind neural networks.
- Apply neural network to solve a real life regression problem.
Workshop 5 - AirBnB Rent Prediction
- This is a realistic regression problem. We try to predict property rental prices in the Boston area. We learn to work with categorical features like neighborhood and property type.
- This workshop also shows the common techniques used to preprocess data.
Workshop 6 - Lung Capacity Prediction
- This is a selfguided workshop. You will be given the dataset and the problem description.
- You will need to solve the problem using a neural network.
Workshop 7 - Logistic Regression Using Gradient Descent
- Learn the theory behind logistic regression (or classification).
- Solve a simple classification problem using Gradient Descent.
Workshop 8 - Titanic Survivability Prediction
- Solve a realistic classification problem using a neural network.
Workshop 9 - Fetal Monitoring Complication Prediction
- Learn the theory behind multi-class classification.
- Solve a medical classification problem using a neural network.
Workshop 10 - Credit Card Fraud Detection
- In this workshop we get deeper into evaluating the quality of a model.
- We learn about Confusion Matrix, Precision and Recall.
Workshop 11 - Epileptic Seizure Recognition
- This is a selfguided workshop. You will be given the dataset and the problem description.
- You will need to solve the problem using a neural network.
Workshop 12 - Basic Convolutional Neural Network (CNN)
- The goal of this workshop is the understand the structure of a CNN. We learn about the convolution layer, max pooling layer, fully connected layer and readout layer. We solve the MNIST handwritten digit comprehension problem.
Workshop 13 - Theory of Convolutional Neural Network
- Learn the theory behind matrix convolution. Observe how convolution works on images.
Workshop 14 - Handwritten Digit Recognition
- Apply CNN to classify handwritten digit images.
Workshop 15 - Solve CIFAR-10 Challenge
- This is a selfguided workshop.
- CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes. We train a CNN that tries to classify images in those 10 classes.