Scribd
Upload
6 views74 pages

M3 Summary

Uploaded by

miiingwu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
6 views74 pages

M3 Summary

Uploaded by

miiingwu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 74

Week 3

Artificial Intelligence Technology Fundamentals—Deep Learning


Video 1: Introduction to Deep Learning
Supervised Learning
Semi-supervised Learning
Unsupervised Learning
Machine Learning Methods – Linear Classifiers

Linear classifiers using the regression and


optimization perspective to include logistic
and support vector machine classifiers
Machine Learning Methods – Non-parametric Methods

• Non-parametric methods
‒ Tree-based approaches
Machine Learning Methods – Probabilistic Frameworks

• Probabilistic frameworks
• Bayesian approaches
Machine Learning Methods – Neural Networks
Video 2: Artificial Neural Network
Neural Networks
Neural Networks (contd.)
Multi-Layer Neural Network
Neural Networks - Definition
Model Coefficients: Example
Gradient Descent
Stochastic Gradient Descent
Gradient Descent: Example
Gradient Descent: Example (contd.)
Gradient Descent: Example (contd.)
Gradient Descent: Example (contd.)
Gradient Descent: Example (contd.)
Gradient Descent: Example (contd.)
Gradient Descent: Example (contd.)
Video 3: Multi-Layer Perceptrons (MLPs)
Neural Networks
Multi-layer Perceptrons
Neural Networks – Non-linear Activation Functions
Neural Networks – Non-linear Activation Functions (contd.)
Neural Networks – Non-linear Activation Functions (contd.)
Neural Networks – Loss Function
Training Multi-Layer Perceptron
Use of Supervised Training and Gradient Descent
Backpropagation
Video 4: Autoencoders
Autoencoders
Autoencoders (contd.)
Autoencoders (contd.)
MNIST Image Dataset
Neural Network
Variational Autoencoders (VAEs)
Variational Autoencoders (VAEs) (contd.)
Video 5: Convolutional Neural Networks (CNNs)
Convolutional Neural Network (CNNs)
Convolutional Neural Network (CNNs) - 1D Convolution
Convolutional Neural Network (CNNs) – 2D Convolution
Convolutional Neural Network (CNNs)
Max Pooling Layers
Max Pooling Layers (contd.)
Other Layers in CNNs
Video 6: Deep Neural Networks (DNNs)
Deep Neural Network (DNNs)
Deep Neural Network (DNNs) ‒ Example
Key Enablers
Challenges with DNNs
Transfer Learning for Small Data Problems
Transfer Learning –Using Pretrained Parameters From a Different Task
Transfer Learning –Using Pretrained Parameters From a Different Task
Transfer Learning –Using Pretrained Parameters From a Different Task
Video 7: Recurrent Neural Networks (RNNs)
Recurrent Neural Network (RNNs)
Recurrent Neural Network (RNNs)
Recurrent Neural Network (RNNs) (contd.)
Recurrent Neural Network (RNNs) (contd.)
Long Short-term Memory (LSTM)
Gated Recurrent Unit (GRU)
Video 8: Machine Learning and Deep Learning
Summary
Unsupervised Learning
Semi-supervised Learning
Supervised Learning
Summary
ML Methods That Are Not Neural Networks
Components of AI

You might also like