Krzysztof Graczyk Homepage
Deep Learning in Physics (Spring 2021)
-
Linear regression in Scikit-learn, implementation in NumPy, introduction to PyTorch
Deep Learning in Physics (Spring 2020)
-
Perceptron, Shallow Neural Networks, Scikit-learn
-
Regression and Classification problems
-
Bias-Variance trade-off
-
PyTorch
-
Analysis of MNIST data with NN
-
Convolutional Neural Networks and MNIST fashion data, LetNet
-
Phase transition in Ising model
-
Regularization, Bootstrap, DropOut, Balanced Sampling, Mean Variance
-
Batch normalization
-
TensorFlow 2.0, Keras
-
Generative Neural Networks
-
ML in Condensed Matter Physics and Particle Physics.
Introduction to neural computations (Spring 2019)
-
Hopfield networks
-
Linear discriminants
-
Single neuron, perceptron
-
Least-square method
-
Multi-layer perceptron, XOR problem, Cybenko theorem
-
Backpropagation of errors
-
Relative entropy
-
Bayesian neural networks
Obliczenia numeryczne i symboliczne, z wykorzystaniem Wolfram Mathematica
|
|
|
|
|
|
|
|
|
|
Neutrinos for layman (in polish)
Clasical Electrodynamics: 2014, 2013, 2012
Coulomb potential and Radiative Corrections