Home | Syllabus | Resources | Assignments |
The tentative syllabus is given below. Please be informed that the timeline and lecture topics are subject to change. For each week, we will regularly update the course material, assignments, and suggested readings.
Week | Date | Description | Readings |
---|---|---|---|
W1 | 20/04 |
Course overview and logistics * The brief history of machine learning and Humanoid robotics * Introduction to FOSS robot simulators * Math and programming resources for multimodal machine learning |
Python/Numpy tutorial DL Book, Part 1 Robot simulators |
W2 | 27/04 |
Intro to machine learning and robotic sensors * ML terminology: targets, features, priors, models, hyperparameters, etc. * Robotic sensors: camera, depth, position encoders, ultrasound, infrared, and lasers * Fantastic mulitmodal datasets and where to find them |
DL Book, Part 1 Dataset search, Kaggle datasets |
W3 | 04/05 |
Intro to neural networks (NNs), multimodal fusion techniques and software stack * Challenges in multimodal learning: data representation and fusion * NN basics: single and multilayer perceptron, parameter initialization, gradient descent, backpropagation, activation and loss functions, etc. * Multimodal fusion techniques: data level, decision level, and intermediate level fusion |
TensorFlow/Keras tutorial DL Book, Ch 6 The pepper robot |
W4 | 11/05 |
Intro to Convolutional Neural Networks (CNNs) * CNNs concepts: convolution, pooling, stride, padding, etc. * CNN architectures: Neocognitron, LeNet, AlexNet, VGGNet, ResNet, etc. * Forming intermediate sensory representation with CNNs |
DL Book, Ch 9 CNN visualizer Feature visualization |
W5 | 25/05 |
Reinforcement learning basics and deep reinforcement learning * RL concepts: Markov decision processes, exploration/exploitation, convergence requirements, model-free methods (e.g., Q learning, SARSA), etc. * Challenges in RL: credit assignment, exploration/exploitation trade-off, etc. * Deep Q Learning variations: DQN, Double DQN, Dueling DQN, DQN experience replay, etc. |
RL Book, Ch 3, Ch 6 Key papers in RL OpenAI RL resources |
W6 | 18/05 |
Intro to unsupervised learning * Applications of unsupervised learning: vector quatization, clustering, feature extraction. * Learning methods: K-Means, competitive learning and self-organizing maps * Unsupervised learning robot architectures: PyEra and SOIMA |
PyEra SciKit Clustering Elements of statistical learning Ch 14.3, 14.4 |
W7-W12 | 01/06-18/07 | Project presentations |
The template was modified by Murat Kirtay by using Mike Pierce's |
© Conference Organizers. |