Overview
Explore Deep Learning with Python and MXNet, including practical demonstrations on a Raspberry Pi for computer vision and natural language processing tasks.
Syllabus
-
- Introduction to AI and Deep Learning
-- Overview of Artificial Intelligence and its applications
-- Basics of Deep Learning and neural networks
-- Introduction to MXNet and its ecosystem
- Getting Started with Raspberry Pi
-- Setting up Raspberry Pi: installation and configuration
-- Installing Python and necessary libraries on Raspberry Pi
-- Introduction to GPIO and Raspberry Pi hardware capabilities
- Python for Deep Learning
-- Python refresher: syntax, libraries, and best practices
-- Using NumPy and Pandas for data manipulation
-- Overview of popular deep learning libraries: MXNet, TensorFlow, and PyTorch
- Deep Learning with MXNet
-- Setting up MXNet on Raspberry Pi
-- Understanding data loading and preprocessing
-- Building and training neural networks with MXNet
-- Implementing Convolutional Neural Networks (CNNs)
- Computer Vision on Raspberry Pi
-- Introduction to computer vision and its applications
-- Setting up and using the Pi Camera module
-- Implementing image classification tasks with MXNet and Raspberry Pi
-- Real-time object detection on Raspberry Pi
- Natural Language Processing (NLP) on Raspberry Pi
-- Overview of NLP tasks and applications
-- Tools and libraries for NLP with MXNet
-- Implementing text classification and sentiment analysis
-- Real-time language translation on Raspberry Pi
- Optimization and Deployment
-- Optimizing deep learning models for Raspberry Pi
-- Techniques for performance improvements: quantization and pruning
-- Deployment strategies for edge devices
- Project: Building an AI-powered Application
-- Define a project scope combining computer vision and NLP
-- Implementing the project on Raspberry Pi
-- Testing and evaluation of the AI application
- Future Trends and Conclusion
-- Discussing future trends in AI and edge computing
-- Course wrap-up and further learning resources
Taught by
Tags
On-Demand
