Last updated: Fall 2025
Lecture Notes:
Lecture 1. Introduction to Neural Networks and Learning Systems pdf
Lecture 2. McCulloch-Pitts Neuron. Concept of Learning.
Hebbian Learning pdf
Lecture 3. Linear Separability. Threshold Neuron.
Error-Correction Learning. Perceptron. pdf
Lecture 4. The simplest feedforward Neural Network and
XOR problem. Hopfield Neural Network pdf
Lecture 5. Sigmoid Activation Function.
Learning based of the learning error minimization.
Feedforward Neural Network (MLP) pdf
Lecture 6. Error Backpropagation. MLP Learning Algorithm pdf
Lecture 7. Pattern Recognition. Classification.
Learning Strategies: learning with validation,
incremental learning, batch learning.
Testing of learning results. Cross-validation pdf
Lecture 8. Complex-Valued Neurons. Multi-Valued Neuron
and its Error-Correction Learning pdf
Lecture 9. Multilayer Neural Network with
Multi-Valued Neurons. Derivative-Free Learning pdf
Lecture 10. Time Series Prediction pdf
Lecture 11. Batch Learning pdf
Lecture 12. Introduction to Deep Learning.
Convolutional Neural Networks. Autoencoders pdf
Lecture 13. Support Vector Machine (SVM) pdf
Lecture 14. Unsupervised Learning. Clustering Techniques pdf