Embark on an enlightening journey into the realm of deep learning with PyTorch through Tertiary Courses. Our meticulously crafted curriculum begins with the foundational step of installing PyTorch, followed by elucidating math operations crucial for complex computations. As we traverse deeper, participants will gain hands-on experience in designing and implementing neural networks, the backbone of any deep learning algorithm.

The course transcends the basics as it immerses students in advanced modules like image recognition through Convolutional Neural Networks (CNNs) and processing sequential data using Recurrent Neural Networks (RNNs). With a blend of theoretical knowledge and practical sessions, this course promises to equip you with the competencies to harness the full potential of PyTorch in deep learning endeavors.

Certificate

All participants will receive a Certificate of Completion from Tertiary Courses after achieved at least 75% attendance.

Funding and Grant

HRD Corp Claimable Course for Employers Registered with HRD Corp

Course Code: M551

Topic 1 Overview of Deep Learning and Pytorch

• Overview of Deep Learning

• Introduction to Pytorch

• Install and Run Pytorch

• Basic Pytorch Tensor Operations

• Computation Graphs

• Compute Gradients with Autograd

Topic 2 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

Topic 3 Neural Network for Classification

• Softmax

• Cross Entropy Loss Function

• Build a NN Classification Model

Topic 4 Convolutional Neural Network (CNN)

• Overview of CNN

• Convolution, Max Pooling and Padding

• Build a CNN Model for Image Classificaiton

• Overfitting Issue with Small Dataset

• Techniques to overcome Overfitting Issue

Topic 5 Transfer Learning

• Introduction to Transfer Learning

• Pre-trained Models

• Feature Extraction & Fine Tuning for Small Dataset

Topic 6 Recurrent Neural Network (RNN)

• Overview of RNN

• Long Term Dependencies

• LSTM and GRU

• Apply LSTM to Time Series Forecasting