Predictive Analytics with PyTorch: Transform Your Data to Prediction
About This Course
This course dives into the practical application of machine learning principles using PyTorch to extract valuable business insights from data. Participants will start with an overview of deep learning and PyTorch, including installation, basic operations, and gradient computation. The curriculum then advances to applying neural networks for regression and classification tasks, teaching how to develop predictive models and prototype classification systems to uncover new insights. Key aspects such as activation functions, loss functions, and optimizers are thoroughly explored to build foundational knowledge in creating efficient machine learning models.
Further, the course delves into the specialized area of Convolutional Neural Networks (CNN) for pattern recognition, providing hands-on experience in building CNN models for identifying trends and patterns. The use of data visualization is highlighted, offering skills in creating interactive visualizations to interpret complex datasets effectively. By the end of this course, participants will be proficient in leveraging predictive data modelling techniques and neural networks to drive decision-making processes, equipped with the ability to use data visualization to enhance data analysis.
What You'll Learn
- apply machine learning principles to gain business insights.
- aggregate data to help test problem using Pytorch.
- apply predictive data modeling techniques to identify underlying trend and - - patterns in data using neural networks.
- develop prototype classification model using machine learning techniques to gain new insight from data.
- identify patterns using convolutional neural network model to derive insights and make decision.
- use Tensorboard data visualisation tool to create interactive visualizations of data.
Course Outline:
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 for Image Classification
Introduction to Convolutional Neural Network (CNN)
Convolution & Pooling
Build a CNN Model for Image Recognition
Topic 5 Data Visualization with Tensorboard
Set up TensorBoard
Inspect a model architecture using TensorBoard
Create interactive Visualizations
Written Assessment (Q&A)
Written Assessment (PP)
Entry Requirements
Knowledge and Skills
• Able to operate computer functions with minimum Computer Literacy Level 2 based on ICAS Computer Skills Assessment Framework
• Minimum 3 GCE ‘O’ Levels Passes including English or WPL Level 5 (Average of Reading, Listening, Speaking & Writing Scores)
Attitude
• Positive Learning Attitude
• Enthusiastic Learner
Experience
• Minimum of 1 year of working experience.
• Minimum 18 years old
Target age group: 21-65 years olf