Generative AI and Machine Learning with Python

Name: Generative AI and Machine Learning with Python
Rating: 4.0 (1 reviews)

Unlock the Power of Machine Learning and Generative AI

Created byYasir Amir

Last updated 3/2025

English

What you'll learn

Implement and evaluate machine learning models in Python.
Apply dimensionality reduction and clustering techniques.
Understand and explain core generative AI models.
Build and train Artificial Neural Networks (ANNs) and Multi-Layer Perceptrons (MLPs) using Keras.

Course content

5 sections • 27 lectures • 19h 30m total length

Introduction Lecture1:36:59
Supervised vs Unsupervised vs Reinforcement Learning
Supervised Learning LAB26:24
Unsupervised Learning LAB36:33
Data Preprocessing1:01:40
Data Preprocessing in Machine Learning
Evaluation Metrics - Accuracy, Precision, Recall, F1-Score56:54
Evaluation Metrics
Evaluation Metrics - Confusion Matrix54:52
Confusion Matrix in Machine Learning

Introduction to Deep Learning and Artificial Neural Network (ANN)59:31
Coding ANN in Python34:53
The Perceptron49:46
Convolutional Neural Networks40:33
Learn convolutional neural networks for image and video data, using convolution, pooling, and fully connected layers with backpropagation and gradient descent for accurate image classification and object detection.
Coding a CNN30:06
Build a cnn on cifar-10 with tensorflow-keras, using conv, max pooling, flatten, and dense layers; train with adam and sparse categorical cross entropy, then evaluate with a confusion matrix.
Implementing MLP with Keras Part 143:39
Launches a Keras sequential API MLP to classify fashion MNIST images using 28 by 28 pixels and 10 classes, with dense ReLU layers and a softmax output.
Implementing MLP with Keras Part 248:06
build a multi-layer perceptron with keras to classify fashion mnist using a sequential model, loading and splitting data, flattening inputs, training with sparse categorical crossentropy, and evaluating with accuracy.
Implementing MLP with Keras Part 322:02
Build a three-hidden-layer MLP with 50 neurons per layer in Keras to predict California housing prices via regression. Use the sequential API, normalization, and mean squared error loss with Adam.
Python implementing of MLP and ANN

Transformer's Attention Mechanism45:14
Explore how transformers use the attention mechanism to compare queries with keys, compute values, and apply self-attention and cross-attention, enabling efficient natural language processing tasks.
Understanding Transformers25:07
Explore how transformers enable fast, context-aware language processing through self-attention, tokenization, and embeddings within an encoder-decoder framework. See how pre-training and fine-tuning shape generative AI for NLP tasks.
Understanding the Generative Adversarial Networks (GANs)26:43
Discover generative adversarial networks, GANs, where a generator and discriminator engage in adversarial training to produce realistic data, with applications in image, video, and text generation.
Transformers and GANs
Understanding Variational Autoencoders (VAEs)34:17
Explore variational autoencoders (VAEs) that encode data into a probabilistic latent space and decode to generate new data, using encoder-decoder pairs, sampling, reconstruction, and KL divergence.
Recurrent Nerual Networks26:01
Explore recurrent neural networks (RNNs) for sequential data, with memory through hidden states and time-step unfolding. Learn LSTM and GRU variants, bi-directional and many-to-many architectures for NLP and time series.
Gated Recurrent Units (GRUs)20:58
Explore GRUs, a simpler RNN variant with reset and update gates that manage memory for text, speech, and time series, addressing vanishing gradients.
GRU, VAEs, Recurrent Neural Networks

Requirements

Basic Programming in Python

Description

Unlock the Power of Machine Learning and Generative AI

This comprehensive course provides a deep dive into the core concepts and practical applications of machine learning and generative AI. Starting with foundational principles like supervised, unsupervised, and reinforcement learning, you'll progress through data preprocessing, evaluation metrics, and essential algorithms like linear and logistic regression, decision trees, and random forests.

Dive into unsupervised learning with K-means clustering and Principal Component Analysis (PCA), mastering dimensionality reduction. Transition to deep learning with Artificial Neural Networks (ANNs), Convolutional Neural Networks (CNNs), and Multi-Layer Perceptrons (MLPs) using Keras.

Finally, explore the cutting edge of generative AI, including Transformer attention mechanisms, Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), Recurrent Neural Networks (RNNs), and Gated Recurrent Units (GRUs).

Course Highlights:

Practical Labs: Hands-on experience coding in Python, solidifying your understanding of key algorithms.
Comprehensive Coverage: From fundamental machine learning to advanced generative AI techniques.
Detailed Evaluation: Learn to assess model performance with various metrics and confusion matrices.
Deep Learning Mastery: Implement and train neural networks using Keras.
Generative AI Exploration: Demystify Transformers, GANs, VAEs, and RNNs.
Regular Quizzes: Reinforce learning with quizzes after each module.

This course is designed for anyone seeking a robust understanding of machine learning and generative AI, from beginners to those looking to expand their knowledge.

Who this course is for:

Anyone interested in AI and Machine Learning

Generative AI and Machine Learning with Python

What you'll learn

Explore related topics

Course content

Introduction6 lectures • 5hr 33min

Module 2 Supervised Learning4 lectures • 3hr 42min

Module 3 Unsupervised Learning3 lectures • 1hr 48min

Module 4 Deep Learning8 lectures • 5hr 29min

Module 5 Generative AI6 lectures • 2hr 58min

Requirements

Description

Who this course is for: