F. Chollet: Deep Learning v jazyku Python, kapitola 2.4.
R. Neruda, J. Šíma: Teoretické otázky neuronových sítí, kapitola 2.1 (volitelný materiál).
P. Sosík: Skripta z neuronových sítí, kapitola 2.1 ( volitelný materiál).
Hluboké učení
Linear classifiers
S. Lazebnik - presentation Linear Classifiers part 1
You can skip everything related to the SVM
S. Lazebnik - presentation Linear Classifiers part 2
You can skip everything related to the SVM
Další studijní materiály
Mean squared error (3 points)
Consider a training set with 30 samples (x_i, y_i) and the loss function Mean Squared Error (MSE) explained in the presentation No. 3 - Linear Classifiers - Part 1. When will the MSE be lower: (a) when the difference between the neuron output w * x_i and the desired value y_i is 1 for each training sample, or (b) when ten samples have the difference 2 and the remaining samples have the difference 0? Justify your answer. Hint: just use the formula for MSE.
Derivative of tanh (4 points)
Assignment description here:
https://www.dropbox.com/scl/fi/l7xpewz2so37l0ar6nk95/Assignment_tanh.png?rlkey=spsbhkllpgl77kig4owht0k7w&dl=0
https://www.dropbox.com/scl/fi/l7xpewz2so37l0ar6nk95/Assignment_tanh.png?rlkey=spsbhkllpgl77kig4owht0k7w&dl=0