- Neural Networks (7 matching lines) [show matches]
title: Neural Networks
# Exercise 2. Convolutional Neural Networks
number of epochs. What do you think of the quality of the network?
What do you think about the quality of the assessment of the network?
You can test the network after each epoch and continue training.
If you do not see the effect of *overtraining*, try to use smaller training sets and see how it changes the behaviour of the network.
Try to change the neural network in Exercise 1 and 2.
- ANN (5 matching lines) [show matches]
title: Neural Networks Lecture
## What is a neural network
+ The network model
+ An automatic differentiation library that is useful to implement neural networks.
+ Neural Networks are Computationally Expensive
- Regression (3 matching lines) [show matches]
title: Neural Networks for Regression
2. Use this class to test if you can train a network to determine the
6. Train and test a neural network to read the digits.
- CNN (3 matching lines) [show matches]
title: Convolutional Neural Networks Lecture
## What is a Convolutional Network
## Sample Network
- Object Detection (2 matching lines) [show matches]
When you have your dataset, try to train the network starting with the pre-trained
Source : [simple tutorial](https://towardsdatascience.com/object-detection-with-neural-networks-a4e2c46b4491) with keras, detecting shapes
