RomanNum3ral
/
AI-For-Beginners
mirror of https://github.com/microsoft/AI-For-Beginners.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
AI-For-Beginners/3-NeuralNetworks/05-Frameworks/lab
History
Dmitri Soshnikov a96da961f9 Add image attributions 2022-04-05 15:34:35 +03:00
..
LabFrameworks.ipynb Add image attributions 2022-04-05 15:34:35 +03:00
README.md Add image attributions 2022-04-05 15:34:35 +03:00

README.md

Classification with PyTorch/TensorFlow

Lab Assignment from AI for Beginners Curriculum.

Task

Solve two classification problems using single- and multi-layered fully-connected networks using PyTorch or TensorFlow:

  1. Iris classification problem
  2. MNIST handwritten digit classification problem

Try different network architectures to achieve the best accuracy you can get.

Stating Notebook

Start the lab by opening MyFW_MNIST.ipynb

Questions

As a result of this lab, try to answer the following questions:

  • Does the inter-layer activation function affect network performance?
  • Do we need 2- or 3-layered network for this task?
  • Did you experience any problems training the network? Especially as the number of layers increased.
  • How do weights of the network behave during training? You may plot max abs value of weights vs. epoch to understand the relation.