Course Outline
Introduction
Overview of TensorFlow
- Understanding the TensorFlow framework
- Key features and capabilities of TensorFlow
Concepts of Artificial Intelligence
- Computational Psychology
- Computational Philosophy
Machine Learning Fundamentals
- Theories of computational learning
- Algorithms for processing computational experience
Deep Learning Explained
- Structure of artificial neural networks
- Distinguishing deep learning from machine learning
Setting Up the Development Environment
- Installation and configuration of TensorFlow
Getting Started with TensorFlow
- Managing nodes in TensorFlow
- Utilizing the Keras API
Fraud Detection Implementation
- Data reading and writing processes
- Feature engineering and preparation
- Data labeling techniques
- Data normalization procedures
- Partitioning data into training and testing sets
- Preparation of input image formats
Prediction Modeling and Regression
- Model loading procedures
- Visualizing predictive outputs
- Generating regression models
Classification Strategies
- Construction and compilation of classifier models
- Model training and evaluation testing
Recap and Final Thoughts
Requirements
- Familiarity with Python programming
Target Audience
- Data Scientists
Testimonials (2)
Hands-on exercises related to content really helps to understand more about each topic. Also, style of start class with lecture and continue with hands-on exercise is good and helpful to relate with the lecture that presented earlier.
Nazeera Mohamad - Ministry of Science, Technology and Innovation
Course - Introduction to Data Science and AI using Python
The training was organized and well-planned out, and I come out of it with systematized knowledge and a good look at topics we looked at