Logistic regression: hyperparameters and cats.
Small talk about hyperparameters and how the influence on test and training error.
Presented by:
Roman
from
PetrSU
I'm a third year student at PetrSU. I am studying machine learning algorithms or more concrete deep learning.
No video of the event yet, sorry!
Deep learning is an active field of research, so i decided to examine some subtleties in this domain. My task was to make a binary classfication network which would be able to distinguish cats from dogs in photos i had. I implemented a logistic regression model and tried out a few architectural decisions such as number of hidden units in different layers, number of these layers and activation functions. I attempted not only to show a difference between these decisions using a classification error but also i wanted to understand reasons of improvements or declines in test and training errors.
- Date:
- 2018 September 21 - 14:30
- Duration:
- 20 min
- Room:
- 311
- Conference:
- Stochastic Modeling and Applied Research of TechnologY
- Language:
- Track:
- Student's Day
- Difficulty:
- Medium