Event Details

Date: 23 – 25 February 2022; In-Person Classroom Training

Venue: Universiti Kuala Lumpur, Gombak, Kuala Lumpur

Trainer: En. Mohd. Harris Lye, Multimedia University, Cyberjaya, Selangor
 

Introduction

Deep Learning is a subfield of Machine Learning (ML) that allows computers to perform tasks like human intelligence, such as speech recognition, image identification, and prediction. It permits machines to solve complex problems while using diverse, unstructured, and interconnected data sets. Deep Learning training helps individuals to improve business scalability and enhance business operations for companies across the globe.

This Deep Learning training provides in-depth knowledge of how to develop their own applications using deep learning techniques effectively. Our highly expert trainer will enable delegates to build complex Deep Learning models that help machines to solve real-world problems.

Day 1:

Topic 1 Overview of Machine Learning & Tensorflow 2.x

• Overview of Machine Learning and Deep Learning
• Introduction to Tensorflow 2.x
• Install Tensorflow 2.x

Topic 2 Basic Tensorflow Operations

• Basic Tensor Data Types
• Constant, Variable & Gradient
• Matrix Operations
• Eagle Mode vs Graph Mode

Topic 3 Datasets

• MNIST Handwritten Digits and Fashion Datasets
• CIFAR Image Dataset
• IMDB Text Dataset

Topic 4 Neural Network for Regression

• Introduction to Neural Network (NN)
• Activation Function
• Loss Function and Optimizer
• Machine Learning Methodology
• Build a NN Predictive Regression Model
• Load and Save Model

Day 2:

Topic 5 Neural Network for Classification

• Softmax
• Cross Entropy Loss Function
• Build a NN Classification Model

Topic 6 Convolutional Neural Network (CNN)

• Introduction to Convolutional Neural Network (CNN)
• Convolution & Pooling
• Build a CNN Model for Image Recognition
• Overfitting and Underfitting Issues
• Methods to Solve Overfitting
• Small Dataset Overfitting Issue
• Data Augmentation & Dropout

Topic 7 Transfer Learning

• Introduction to Transfer Learning
• Pre-trained Models
• Transfer Learning for Feature Extraction & Fine Tuning
• Tensorflow Hub

Day 3:

Topic 8 Recurrent Neural Network (RNN)

• Introduction to Recurrent Neural Network (RNN)
• Types of RNN Architectures
• LSTM and GRU
• Word Embedding
• RNN Model for Sentiment Analysis
• RNN Model for Time Series Prediction

Topic 9 Practical Mini Project