SubjectsSubjects(version: 978)
Course, academic year 2025/2026
   Login via CAS
   
Neural networks, machine learning, and randomness - NAIL138
Title: Neuronové sítě, strojové učení a náhodnost
Guaranteed by: Department of Theoretical Computer Science and Mathematical Logic (32-KTIML)
Faculty: Faculty of Mathematics and Physics
Actual: from 2025
Semester: winter
E-Credits: 3
Hours per week, examination: winter s.:1/1, C+Ex [HT]
Capacity: unlimited
Min. number of students: unlimited
4EU+: no
Virtual mobility / capacity: no
State of the course: taught
Language: Czech
Teaching methods: full-time
Guarantor: prof. RNDr. Ing. Martin Holeňa, CSc.
Teacher(s): prof. RNDr. Ing. Martin Holeňa, CSc.
Annotation -
Stochastic methods are extremely important for the construction and training of neural networks and other machine learning models. This course will discuss in depth a number of types of neural networks that rely on randomness, and specific stochastic methods for neural networks and machine learning. Near the end, it explains the general stochastic approach to training neural networks and shows that machine learning models, including neural networks, are used in one of the most important applications of randomness – stochastic optimization methods, which include e.g. evolutionary algorithms.
Last update: Hric Jan, RNDr. (15.05.2025)
Aim of the course -

Systematic clarification of the connections between stochastic methods and training of neural networks or other machine learning models. An introduction to specific types of neural networks that rely substantially on randomness and to stochastic methods for neural networks and machine learning that a student does not learn in the courses of probability and statistics.

Last update: Hric Jan, RNDr. (19.05.2025)
Syllabus -
1. Recalling concepts known from other courses
Artificial neural networks, signal transmission, network architecture. Best known types of neural networks. General models in machine learning. Model training. Model selection. Selection of features. Measures of model quality. Interpretability and explainability. Supervised and unsupervised learning, reinforcement learning. Best known supervised learning methods. Rules learning. Clustering. Random variables and random processes. Probability distributions and moments. Bayesian approach.

2. Artificial neural networks based on randomness
ELM (extreme learning machine) networks. Learning ELM networks, the optimization task for learning ELM networks. ELM networks and random projection. Randomized convolutional neural networks. ESN (echo state network) networks. Evolution of activity in ESN networks. ESN networks with inhibit connections. Bayesian Neural Network (BNN). A priori probability distribution in a BNN. Predictions and estimates in a BNN. BNN with stochastic activation, BNN with bounded stochasticity, hierarchical BNN.

3. Stochastic methods for artificial neural networks
Dropout, Bernoulli dropout, properties of Bernoulli dropout. Dropout and network learning, dropout and regularization. Dropout and neural network teams. Dropout in Boltzmann machines and in linear regression. Gaussian dropout. Stochastic gradient. Stochastic gradient descent (SGD). Assumptions and strategies of the SGD method. Approximation of posterior probability distribution, approximation by components.

4. Stochastic methods for machine learning
Observable and latent variables. Monte Carlo Markov chain (MCMC). MCMC estimation of the posterior distribution of latent variables. Metropolis-Hastings algorithm. Variational inference (VI). VI estimation of the posterior distribution of latent variables. Evidence lower bound. Combining VI with MCMC. VI estimates in generative models, deep Kalman filters.

5. General stochastic approach to artificial neural networks
Assumptions of the general stochastic approach. Spaces of random vectors. Mean-based learning and random-based learning. Specificity of mean-based learning under quadratic error function. Strong law of large numbers for neural network learning, assumptions and assertions. Central Limit Theorem for Learning Neural Networks, assumptions and assertions. Connection with testing the zeroness of connection weights, use in network pruning.

6. Machine learning and neural networks as support for stochastic optimization
Stochastic optimization algorithms, the evolutionary algorithm CMA-ES (covariance matrix adaptation evolution strategy). Disadvantage of stochastic optimization for black-box objective functions with costly evaluation. Surrogate modeling for black-box optimization. Choice of evaluation between black-box function and model. Surrogate models based on artificial neural networks, Gaussian processes, random forests and ordinal regression.

Last update: Hric Jan, RNDr. (19.05.2025)
 
Charles University | Information system of Charles University | http://www.cuni.cz/UKEN-329.html