Deep Learning Hands On
Deep Learning Hands On
Deep Learning Hands On
Deep Learning
Nurulaqilla Khamis
Skymind Holdings Berhad
(XpressAI Sdn Bhd)
Doctor of Philosophy (PhD)
Master of Philosophy (MPhil)
Nurulaqilla Khamis
Deep Learning Engineer
Bachelor of Engineering
Electrical Electronics (B.Eng)
CONTENTS
1. Recap on Machine Learning (ML) & Deep Learning (DL)
2. Deep Learning Pipeline
3. Integrated Development Environment (IDE) & Dependencies
4. Deep Learning Frameworks
5. Deep Learning Model (Hands-On using Google Colab)
Image Classification Problem
UNSUPERVISED
Clustering Problem
LEARNING
• Data don’t have label
• Learn without label data
• Capture the data
characteristics, pattern
REINFORCEMENT
LEARNING
• Learn make decision
through reward by trial &
RECAP ON ML & DL (Cont.)
NEURAL NETWORK
RECAP ON ML & DL (Cont.)
What Makes Neural Network Not Preferable
To Process Images?
Image Size = 28 x 28 x 1
(width, height, channel)
Drawbacks:
1. Complex nodes and network
2. Huge # of Parameters (Weights),
Channel – 1 (Grayscale Image) tend to overfitting
Channel – 3 (RGB Image)
7 x 7 x 40 = 1960 neurons
Pre-installed dependencies/libraries
Saved on the cloud
Link with GitHub
Free GPUs and TPUs
DEEP LEARNING MODEL (IMAGE
CLASSIFICATION)
Let’s Get Started!
1. Data Acquisition
MNIST Dataset (Handwritten Digit Classification
Problem)
10 classes image
6. Model Evaluation
DEEP LEARNING MODEL
(SENTIMENT ANALYSIS)
Let’s Get Started!
1. Data Acquisition
IMDB Dataset (Movie Review Dataset)
2 classes sentiment polarity
6. Model Evaluation
TAKE HOME MESSAGE
https://skymind.global/
https://skymind.global/deep-learning-certification/
[email protected]