Machine Learning

Learn how artificial intelligence helps algorithms improve on their own.

Categories

Data Courses

Machine Learning:


Artificial Intelligence (AI): This module is an introduction to artificial intelligence. It covers the representation scheme of intelligent agents by explaining how to represent problems in a state-space graph, and how to implement searching algorithms to solve these problems. Showing how to describe states in terms of features, we study constraint satisfaction problems, and we explain how constraint satisfaction problems can be solved with search.

Decision Trees: This module focuses on machine learning using decision trees. It covers a variety of decision trees algorithms such as ID3, CART, and random forests. Moreover, this module provides decision trees programming examples with python.

Deep Learning: This module covers Deep Learning, a neural network with “many” hidden layers. Deep Learning is a Statistical Learning algorithm that is often used in a variety of predictive analytics systems.  This module covers regression, neural networks and statistical learning model.

Deep Learning with PyTorch: This module covers the basics of Pytorch. Pytorch is a Python library for deep learning and machine learning programming. The module focuses on Tensors the basic data structure in Pytorch and explains how to design and implement Neural Network models using Pytorch.

Deep Learning with TensorFlow: This module introduces the basics of deep neural networks using TensorFlow. It focuses on the implementation of linear regression, convolutional neural networks, and recurrent neural networks using TensorFlow.

Machine Learning, Fundamentals: Development 2021

Natural Language Processing (NLP): This module introduces the basics of natural language processing NLP. In details, it covers regular expressions, and N-gram models. Moreover, this module reviews sentiment analysis as an NLP example

Reinforcement Learning: This module introduces different reinforcement learning methodologies, including Markov decision process, Monte-Carlo methods, temporal-difference method, state-action-reward-state-action (SARSA), and Q-learning.

Supervised Learning: This module covers a variety of supervised learning methods, such as Naïve Bayesian, Neural Networks, Support Vector Machines, Decision trees, and K-Nearest Neighbors. Also, this module reviews the programming implementation of these methods using Scikit-Learn Python Library.

Unsupervised Learning: This module covers unsupervised learning and focuses on two clustering algorithms: K-Means clustering and Hierarchical clustering. Moreover, this module shows examples about how to implement clustering algorithms using Scikit-Learn python library.

 

If you are external to the Minnesota State System, please complete the Interest Form.

Access: 1.) Click below to be redirected to D2L and sign on with your StarID and password. Then, select Self-Registration and choose from the ITCOE courses listed. 2.) If you are external to the Minnesota State System, please complete the Interest Form below.

Click Here to Go to D2L