Second Semester
Fri: 11:00 a.m. - 1:00 p.m., Aula E2
Fri: 2:00 p.m. - 4:00 p.m., Aula B2
Introduction [pdf]
AI spring? Artificial Intelligence, Machine Learning, Deep Learning: facts, myths and a few reflections.
Fundamentals: Artificial Neural Networks [pdf]
Foundations of machine learning: dataset, representation, evaluation, optimization. Feed-forward neural networks as universal approximators.
Flow Graphs and Automatic Differentiation [pdf]
Tensorial representation, flow graphs. Automatic differentiation: graphs from graphs.
Aside 1: Tensor Broadcasting [pdf]
From theoretical tensor algebra to actual computation: operators and automatic broadcasting.
Deep Networks [pdf]
Deeper networks: potential advantages and new challenges. Tensorial layerwise representation. Softmax and cross-entropy.
Shannon Entropy (Wikipedia)
Cross Entropy (Wikipedia)
Learning as Optimization [pdf]
Vanishing and exploding gradients. First and second order optimization, approximations, optimizers. Further tricks.
Aside 2: Exponential Moving Average [pdf]
Aside 3: Predictors [pdf]
From in-sample optimization to out-of-sample generalization.
Convolutional Networks [pdf]
Convolutional filter, filter banks, feature maps, pooling, layerwise gradients.
Aside 4: Hardware for Deep Learning [pdf]
Main differences bewtween CPUs and GPUs, SIMT parallelism, bus-oriented communication, a few caveats.
Deep Convolutional Neural Networks and Beyond [pdf]
Some insight into what happens in convolution layers. DCNN architectures. Transfer learning. Working in reverse: image generation. Generative adversarial networks. Autoencoders and segmentation. Object detection.
Deep Learning and Time Series [pdf]
Recurrent Neural Networks (RNN), temporal unfolding, LSTM Cells, GRU cells, encoder / decoder, convolution, time series analysis-
Reinforcement Learning [pdf]
A short recap about RL foundations, Markov decision process, state value function, policy, optimality, action value function, Q-learning.
Deep Reinforcement Learning [pdf]
Integrating DNNs into the RL paradigm, DQN algorithm, policy gradient, actor-critic method, NAF algorithm-
Aside 5: Word Embedding [pdf]
Skip-grams, probability distribution of context and center words, training and results, continuous bag of words (CBOW) model.
Monte Carlo Tree Search [pdf]
Game trees, Monte Carlo strategy, Monte Carlo Tree Search (MCTS), Upper Confidence Bounds applied to Trees (UCT).
Alpha Zero [pdf]
MCTS + DNN, network architecture, replacing MCTS rollout with estimation, network training, AlphaZero in continuous spaces (hints).
Attention and Transformers [pdf]
Attention as a kernel, attention maps, queries, key and values, attention-based encoder and decoder, transformer architecture, translator.
Marco Piastra
Contact: marco.piastra@unipv.it