The task is to train a binary classifier on a subset of the MNIST set, in which we distinguish classes (digits 0 and 1 are to be excluded from the set):
First numbers (2,3,5,7)
Compound numbers (4,6,8,9)
Write an efficient implementation of the logistic regression model trained by the SGD algorithm with momentum. You have to write the whole training process yourself, in Python language, using the library numpy. It is not allowed to use ready-made implementations of optimizers and models as well as libraries for automatic function differentiation (e.g. Tensorflow, pytorch, autograph).
Select hyperparameters in order to get the best possible result on the validation set. Draw and save conclusions from your experiments.
DescriptionIn this final assignment, the students will demonstrate their ability to apply two ma
Path finding involves finding a path from A to B. Typically we want the path to have certain properties,such as being the shortest or to avoid going t
Develop a program to emulate a purchase transaction at a retail store. Thisprogram will have two classes, a LineItem class and a Transaction class. Th
1 Project 1 Introduction - the SeaPort Project series For this set of projects for the course, we wish to simulate some of the aspects of a number of
1 Project 2 Introduction - the SeaPort Project series For this set of projects for the course, we wish to simulate some of the aspects of a number of