Artificial Intelligence and Deep Learning with Python

U1: Fundamentals of AI and Deep Learning

• Fundamentals of Machine Learning and Deep Learning
• Setting up Python and Libraries for Deep Learning
• Introduction to supervised learning
• Understanding overfitting and underfitting in supervised learning
• Metrics for evaluating Classification models
• Ethics for evaluating regression models
• Introduction to unsupervised learning

U2: Creation of Artificial Neural Networks (ANN)

• Basics of neurons and perceptrons
• Fundamentals of neural networks
• Different activation functions
• Activation functions for multiclass models
• Cost Functions and Gradient Descent
• How backpropagation works
• Strategies for designing effective neural networks
• Advantages of using Tensorflow and Keras
• Practical case of regression with Keras
• How to import libraries and fonts in Keras
• Data analysis and preprocessing in Keras (I)
• Data analysis and preprocessing in Keras (II)
• Data splitting in Train and Test with Keras
• Data scaling in Keras
• Creating Regression Models in Keras
• Training Regression Models in Keras
• Evaluation and Prediction in Regression with Keras
• Practical case of Binary Classification with Keras
• Importing libraries and fonts for Binary Classification
• Data analysis and preprocessing for
• Binary classification
• Data splitting into Train and Test for Binary Classification
• Data Scaling for Binary Classification
• Creating Binary Classification Models
• Training Binary Classification Models
• Evaluation and Prediction in Binary Classification with Keras
• Multiclass Classification Case Study with Keras
• Importing libraries and fonts for Multiclass Classification
• Data analysis and preprocessing for multiclass classification (I)
• Data analysis and preprocessing for multiclass classification (II)
• Data Splitting into Train and Test for Multiclass Classification
• Data Scaling for Multiclass Classification
• Creating Multiclass Classification Models
• Training Multiclass Classification Models
• Evaluation and Prediction in Multiclass Classification with Keras
• Model monitoring with Tensorboard

U3: Creation of Convolutional Neural Networks (CNN)

• Convolutional Neural Networks (CNN) Basics
• Image filters and kernels in CNN
• Convolutional layers in neural networks
• Pooling layers in neural networks
• Black and White Image Classification Case Study
• Importing libraries and fonts for Black and White Image Classification
• Black and White Image Preprocessor
• Creating models for Black and White Image Classification
• Training models for Black and White Image Classification
• Evaluation and Prediction in Black and White Image Classification
• RGB Image Classification Case Study
• Importing libraries and fonts for RGB image classification
• RGB image preprocessing
• Creating models for RGB image classification
• Training models for RGB image classification
• Evaluation and Prediction in RGB Image Classification

U4: Creation of Recurrent Neural Networks (RNN)

• Introduction to Recurrent Neural Networks (RNN)
• LSTM Neural Networks
• Creating batches in RNN
• Forecasting with RNN practical case
• Importing libraries and sources for Forecasting with RNN
• Data preprocessing for Forecasting with RNN
• Data splitting in Train and Test for Forecasting with RNN
• Data Scaling for Forecasting with RNN
• Creating Time Series Generators for Forecasting with RNN
• Development of Forecasting models with RNN
• Training Forecasting Models with RNN
• Evaluation and Prediction in Forecasting with RNN

U5: Creation of Neural Networks in Unsupervised Learning

• Basics of unsupervised neural networks
• Introduction to autoencoders in neural networks
• Unsupervised neural networks case study
• Importing libraries and sources for unsupervised neural networks
• Data preprocessing for unsupervised neural networks
• Scaling in unsupervised neural networks
• Estimating the number of clusters for unsupervised neural networks
• Building the model for unsupervised neural networks
• Model training for unsupervised neural networks
• Evaluation and prediction for unsupervised neural networks

U6: Conclusions

• Conclusions

Course evaluation

• This course contains a final exam

G-Tools: For Students

• Exclusive access to cutting-edge student tools: improve your employability, participate in exclusive events, take advantage of our intelligent virtual assistant, and more.

⚑ Certificate of completion

• Your personalized digital certificate, a unique badge of your achievements, with international validity, course duration and QR code for instant verification.