An AI Engineer's Guide to Machine Learning with Keras

Dive into deep learning with Keras in this comprehensive 35-minute tutorial. Learn to build and train machine learning models for heart disease prediction using Google Colab and Jupyter notebooks. Start with data import and exploratory data analysis, then progress through data splitting, transformation, and model setup. Visualize network architecture, implement callback functions for real-time performance tracking, and compare models trained with and without validation data. Master techniques for compiling, training, and evaluating model performance. Gain hands-on experience with ready-to-use code available on GitHub, suitable for local execution or Google Colab. Perfect for AI engineers looking to enhance their skills in deep learning with Keras.

video start
Content intro
Google Colab and notebook Intro
05:26 1st Notebook model with only training data
Data Import
EDA Exploratory Data Analysis
Data Split Train and Target
Training data Transformation
Train and Test Data Split
Setup model network and layers
Network Visualization
Callback function to plot loss per epoch
Compile Model
Start Model Training
Callback function to plot loss & accuracy per epoch
Check model loss and accuracy in real time
Validate Model History
Check Model Performance
27:17 2nd Notebook model with training & validation data
Training data split into Train & Validation data
Compile Model & start Model Training
Check model loss and accuracy with validation in real time
Check Model Performance
Saving colab notebook to Github
Credits