Download presentation
Presentation is loading. Please wait.
Published byKristopher Reeves Modified over 6 years ago
1
FUNDAMENTALS OF MACHINE LEARNING AND DEEP LEARNING
An introduction Presented by Dr. Stephen Gbenga Fashoto. Department of Computer Science, Faculty of Science & Engineering University of Swaziland.
2
Machine Learning Supporting Disciplines
3
Fundamentals of Machine Learning
Developed from Artificial Intelligence The first artificial neuron learning is the perceptron by Frank Rosenblatt 1957 Key Elements of Machine Learning Representation: how to represent knowledge. Evaluation: the way to evaluate performance using metrics. Optimization: it is used to determine the optimal result. Historical Perspective Supervised Machine Learning Unsupervised Machine Learning Semi - supervised Machine Learning Reinforcement Machine Learning Deep Learning
4
Supervised Machine Learning
What is SML Goal of SML Classification of SML Problems Examples of SML Algorithm are : Linear regression for regression problems Neural networks for classification and regression problems. Random forest for classification and regression problems. Support vector machines for classification problems. Regression 3D Classification Reflection Reflection
5
Text, Graphics & Pictures
6
Unsupervised Machine Learning
What is UsML Goal of UsML Classification of UsML Problems Examples of UsML Algorithm are : k-means for clustering problems. Apriori algorithm for association rule learning problems. Clustering 3D Association Reflection Reflection
7
Text, Graphics & Pictures
8
Semi supervised Machine Learning
Clustering What is S-SML Goal of S-SML 3D Reflection Association Reflection
9
Text, Graphics & Pictures
10
Reinforcement Learning
Regression What is RL Goal of RL Steps in RL Examples of RL Algorithm are : Q-Learning Temporal Difference (TD) Deep Adversarial Networks 3D Reflection Reflection Classification
11
Deep Learning Algorithms
Regression What is DL Goal of DL Steps in DL Examples of DL Algorithm are : Deep Boltzmann Machine (DBM) Deep Belief Networks (DBN) Convolutional Neural Network (CNN) Stacked Auto-Encoders Recurrent Neural Network(RNN) 3D Reflection Reflection Classification
12
Convolutional Neural Network (CNN)
Regression Introduction to CNN Application of CNN 3D Reflection Reflection Classification
13
Performance of Machine Learning Under – fitting Graph
Clustering 3D Reflection Association Reflection
14
Over – fitting Graph Clustering 3D Reflection Association Reflection
15
Generalization Graph Clustering 3D Reflection Association Reflection
17
Comparison of Machine Learning and Deep Learning
Data dependencies Hardware dependencies Execution time
18
PRACTICAL SESSION ON WEKA 3.8.2
DEMO
19
Thank you for listening
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.