Machine Learning School

M1-INTRO: Introduction to Artificial Intelligence and Machine Learning M2-DATA-ANALYSIS: The Data Analysis Process M3-SIMPLE-ML: Introduction to Simple Machine Learning Methods M4-CLUST: Cluster Analysis M5-CONVEX-OPTI: Convex Optimization M6-OPTI-LEARN: Optimization-based Machine Learning M7-EVAL: Evaluating Model Performance M8-INTERPRET-TABULAR: Interpretability of Models on Tabular Data M9-AUTODIFF-ANN: Introduction to Neural Networks and Automatic Differentiation M10-DEEP-LEARN: Deep Learning M11-DEEP-LEARN-ADVANCED: Advanced Approaches in Deep Learning M12-INTERPRET-DEEP: Interpretability Methods for Deep Learning
M13-DEEP-LEARN-SEQ: Deep Learning for Sequential Data
M14-ENSEMBLE: Ensemble Methods M15-DIMRED: Dimensionality Reduction M16-EMBED: Embeddings M17-GP-HYPEROPT: Gaussian Processes and Hyperparameter Optimization M18-RL: Reinforcement Learning M19-DEEP-RL: Deep Reinforcement Learning M20-SVM: Support Vector Machines M21-SEARCH: Search Methods M22-ADVERSARIAL-SEARCH: Search Methods in Adversarial Contexts M23-METAHEURISTICS: Metaheuristic Optimization M24-STATE-SPACE: State-space Approaches in Control M25-BAYES-NET: Bayesian Networks M26-GAMING: AI and Gaming M27-FAIRNESS: Fairness in Machine Learning Team Project

M13-DEEP-LEARN-SEQ: Deep Learning for Sequential Data

11h 0min
Learning tasks for sequential data; recurrent neural networks + backpropagation through time; sequential attention; transformer, perceiver, perceiver-IO
Main Content - Copy
Acquisition
1 Lecture content
Content: – Deep learning for sequential data; – Training recurrent neural networks using BPTT; – Recurrent architectures: LSTM, GRU; – Sequential attention; – Transformer, Perceiver, Perceiver IO; – The basics of how to work with time series; – Applications; – ...
2h 0min
Practice
2 Colab Notebooks
A set of colab notebooks, regarding e.g. these topics: – Applications, e.g. an example of doing OCR, machine translation, etc.; – Fine-tuning a language model (BERT, GPT), e.g. to Shakespeare’s texts; – Fine-tuning a language model to a classification task, e.g. to IMDB; – LSTMs and time series; – Forecasting: ARMA, LSTM, XGBoost, ...; – Optionally also time series decomposition, etc.; – ...
3h 0min
0
Investigation
3 Independent study time + review
The estimated additional time required for studying the material independently, using the lecture videos/slides and also referencing other literature and material, as necessary. Facilitates correct understanding of the material. This activity also includes the time required for review before exams.
5h 30min
Assessment
4 Quiz activities
Quiz activities meant to provide quick, unassessed feedback to students regarding their grasp of the material.
30 min

 

2025 © Faculty of Organization and Informatics

Terms of Service and Privacy notice

Decorative image (arrow)
Contact us learning-design@foi.hr