Pattern-Recognition-Machine-Learning:

The goal is to try and test some Pattern Recognition, Machine Learning Algorithms Plus some implementations with Tensorflow

This Pattern Recognition Course, Offered by Prof. Cheehung Henry Chu in Spring 2019 with the following syllabus: (CSCE_509/lecture Slides 01.pdf,02,04,06)

However, later I searched more and reviewed some other complimentary materials that I would like to list them here as well: A very close syllabus to what we covered in our class has been offered at university of Waterloo by Prof. Ali Ghodsi. It's tiltle is: Statistical Learning- Classification All Slides and videos are available in the following link:

https://uwaterloo.ca/data-analytics/statistical-learning-classification

Syllabus:

1- Introduction: What is pattern recognition. Basic example. Probability concepts; events, probability, random variables, expected values. Decision rule. 2-Linear Classifier: 3-Unsupervised Learning 4-Non-parametric Supervised Learning 5-DBSCAN clustering 6-Multilayer Neural Networks 7-Linear Regression and TensorFlow Implementations

9-Artificial Neural Networks and TensorFlow Implementations

Main References:

-Pattern Recognition and Neural Networks: By B.D. Ripley, Cambridge University Press. ISBN 0 521 46086 7. January 1996. http://www.stats.ox.ac.uk/~ripley/PRbook/#Contents

-Trevor Hastie, Robert Tibshirani, Jerome Friedman: "The Elements of Statistical Learning" (2nd edition), 745 pages, Springer, 2009 (online version)

-Richard O. Duda, Peter E. Hart, David G. Stork: "Pattern Classification" (2nd edition), 680 pages, Wiley, 2000 (online version)

Crash Course Section Introduction:

NumPy Crash Course

Pandas Crash Course

Data Visualization Crash Course

SciKit Learn Preprocessing Overview

TensorFlow Basics:

-TensorFlow Basic Syntax:The related code to practice this part is called: Tens_Basic.npy.

-TensorFlow Graphs: The related code to practice this part is called: TensGraphs.ipynb.

-Variables and Placeholders: The related code to practice this part is called: Var_Placehold.ipynb(.npy).

-TensorFlow - A Neural Network: The related code to practice this part is called: 03-TF-Neural-Network.ipynb

-TensorFlow Classification Example: The related code to practice this part is called: 05-TensorFlow-Classification-Example.ipynb And Works with pima-indians-diabetes.csv

-TensorFlow Regression Example: The related code to practice this part is called: 04-TensorFlow-Regression-Example.ipynb

Another Pattern Recognition Class Link(2012):

https://www.youtube.com/playlist?list=PLuRaSnb3n4kRDZVU6wxPzGdx1CN12fn0w

Lecture Slides for Machine Learning from Department of Computer Science and Engineering, University at Buffalo:

The slides were last updated in Fall 2018. Instructor: Sargur Srihari

https://cedar.buffalo.edu/~srihari/CSE574/

Learning Theory, Course Instructor: Reza Shadmehr

Spring semester 2017

http://courses.shadmehrlab.org/learningtheory.html