KOM4520 Robotic Vision Week {1-4}
KOM4520 Robotic Vision Week-1 Introduction
KOM4520 Robotic Vision Week-2 pose and orientation
KOM4520 Robotic Vision Week-3 Mobile Robot Vehicles
KOM4520 Robotic Vision Week-4a Mobile Robot Vehicles
KOM4520 Robotic Vision Week-4b Image Formation
KOM4520 Robotic Vision Week-5a Image Operations
KOM4520 Robotic Vision Week-5b Image Features
KOM3570 Image Processing in Industrial Systems Week {1-6}
KOM3570 Image Processing in Industrial Systems W1 Introduction
KOM3570 Image Processing in Industrial Systems W2 Point-Based Processing
KOM3570 Image Processing in Industrial Systems W3 Image Filters
KOM3570 Image Processing in Industrial Systems W4 Sharpening Filters FreqDomain
KOM3570 Image Processing in Industrial Systems W5 Freq Domain Filtering [a]
KOM3570 Image Processing in Industrial Systems W5 Morphological
Canny Edge Detector
----------------
# install Python 3.10.9 (or a newer version)
# on cmd.exe
python get-pip.py
#get-pip.py is under JupyterLabProjects folder
pip install opencv-python
pip install jupyterlab
python -m pip install -U matplotlib
# on cmd.exe type,
jupyter-lab
KOM6110 ANN Machine Learning Week {1-7}
KOM6110 ANN_Machine_Learning Week 1 Introduction
KOM6110 ANN_Machine_Learning Week 2 Intro Knowledge-Learning
KOM6110 ANN_Machine_Learning Week 3 Perceptrons
KOM6110 ANN_Machine_Learning Week 4 Perceptrons II
KOM6110 ANN_Machine_Learning Week 5 Bayes
KOM6110 ANN_Machine_Learning Week 6 Bayes II
KOM6110 ANN_Machine_Learning Week 7 CNN deep learning
-----
# install Python 3.10.9 (or a newer version)
# on cmd.exe
python get-pip.py
#get-pip.py is under JupyterLabProjects folder
pip install opencv-python
pip install jupyterlab
python -m pip install -U matplotlib
# on cmd.exe type,
jupyter-lab
KOM6110 ANN_Machine_Learning Assg 1 Spring 2024
...... There is a correction regrading the 1st question.
1) ...
a) Create a
suitable perceptron (a single unit)
structure
b) Train it
with perceptron learning using Standard Approximation, and test it
with the test data.
c) Train it
with perceptron learning using Stochastic Approximation, and test
it with the test data.
d) Train it
with delta rule which uses gradient descent and Standard Approximation,
and test it with the test data.
e) Train it
with delta rule which uses gradient descent and Stochastic Approximation,
and test it with the test data
f) Get
related figures to display data distribution, classification for training data,
classification for test data, training
error vs iterations
(Stochastic
Approximation or Standard Approximation is
about the way you update the weights)
(refer to Week3, slides 13 and 14)