Introduction to Embedded AI :
What is an Artificial intelligence?
What is Machine Learning?
What is Deep Learning?
What is an Embedded/Edge AI?
Applications of Embedded AI
Tools Used and Installation :
Overview of the Tools used.
What is Tensorflow?
What is Keras?
Comparison between Keras and Tensorflow
Installation of Keras and Tensorflow
What is STM32 and X-CUBE AI
Development Board used
Basic Concepts of AI and Deep Learning :
What is Supervised Learning?
What is Unsupervised Learning?
Artificial Neuron Vs Real Neuron
What is an Artificial Neural Network?
What are layers and Forward propagation in NN
What is an Activation Function?
What is Gradient and Gradient Descent?
Optimization Algorithm and Loss function
How a Neural Network Learns?
The Concept of Loss functions in detail
The process of training and testing a NN
Why Overfitting occurs in NN and How to avoid it?
Why Underfitting occurs in NN and How to avoid it?
Hyperparameter of NN -> Learning Rate
What is Batch and Batch size of a Training samples?
Transfer Learning and Fine tuning Hyperparametrs in NN
What is Convolution?
What is a Convolution Layer in NN?
What is Max Pooling Layer?
What is Dropout layer?
One Hot Encoding of Output Classes or Labels
What is Confusion Matrix?
Difference between with or without normalization Confusion matrix
Introduction to Python and Python Packages Used :
Introduction To Python and Writing first Program
Inroduction to Numpy Package
Introduction to Pandas Package
Introduction to Matplotlib
Building Practical Application (Fault Recognition of a Motor on Edge) :
Key Steps for the implementation of Edge AI
Data Capturing from Sensors (Practical) :
Accelerometer Sensor Module
C code to capture data from Accelerometer
Python Script to Collect and Save Data in Binary file
Data Cleaning and Labeling (Practical) :
Python script to Clean and Label Data
Building and Training of a Neural Network (Practical) :
Defining a Convolution Neural Network to Learn from Captured Data
Python Script to Train the Neural Network
How we captured data and trained the model on it
Performance Evaluation of the Model (Plotting Confusion Matrix)
Conversion of Model to C code (Practical) :
Convert KERAS model to c code
Integration of generated c code to acccelerometer module code
Infer the Result (Practical) :
Infer the Fault State on the machine (demo)
There are currently no items in your shopping cart.