Ágnes Vathy-Fogarassy, PhD
Prerequirements:
- Artificial intelligence (MSc)
Topics covered:
Students will learn about the following topics, including their individual training plans and interests:
T1. Neural Networks
- teaching neural networks, backpropagation, parameters, hyper-parameters and hyperparameter-tuning, regularisation, optimizing convergence
T2. Recurrent Neural Networks (RNN)
- the structure of RNNs, the effect of recurrent links, types of RNNs and their application, Bidirectional RNN (BRNN), Deep RNN (DRNN)
- Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM)
T3. Other types of networks and their application
- neural networks in ranking: RankNet, LambdaRank, LambdaMART
- siamese neural networks
- few-shot learning, one-shot learning
Literature:
- Ian Goodfellow, Yoshua Bengio, Aaron Courville: Deep Learning, MIT Press (2016)
- Stanford University: Recurrent Neural Networks https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-recurrent-neural-networks#word-representation