This repository contains a recap of my progress and learnings from the following Coursera specializations:
- Machine Learning Specialization
- DeepLearning.AI Specialization
- TensorFlow Data and Deployment Specialization
This specialization provided a comprehensive overview of machine learning algorithms and techniques. It consisted of the following courses:
-
Course 1: Machine Learning Foundations: A broad introduction to the field of machine learning, covering topics such as linear regression, classification, and model evaluation.
-
Course 2: Machine Learning: Regression: Explored regression algorithms including linear regression, polynomial regression, and regularization methods.
-
Course 3: Machine Learning: Classification: Focused on classification algorithms, such as logistic regression, decision trees, and random forests.
-
Course 4: Machine Learning: Clustering & Retrieval: Covered unsupervised learning techniques like clustering, dimensionality reduction, and recommender systems.
-
Course 5: Machine Learning: Recommender Systems & Dimensionality Reduction: Delved deeper into recommender systems and advanced dimensionality reduction methods.
-
Course 6: Machine Learning Capstone: An opportunity to apply the knowledge gained throughout the specialization to a real-world project.
The DeepLearning.AI specialization provided a comprehensive understanding of deep learning algorithms and their applications. It consisted of the following courses:
-
Course 1: Neural Networks and Deep Learning: Introduced the fundamental concepts of neural networks, deep learning, and their building blocks.
-
Course 2: Improving Deep Neural Networks: Hyperparameter tuning, regularization, and optimization techniques were explored to improve model performance.
-
Course 3: Structuring Machine Learning Projects: Discussed best practices for designing and structuring machine learning projects.
-
Course 4: Convolutional Neural Networks: Focused on convolutional neural networks (CNNs) and their applications in image recognition and computer vision.
-
Course 5: Sequence Models: Covered sequence models such as recurrent neural networks (RNNs) and long short-term memory (LSTM) networks.
-
Course 6: DeepLearning.AI Capstone Project: Implemented a deep learning model on a real-world project to solve a specific problem.
The TensorFlow Data and Deployment specialization focused on practical aspects of using TensorFlow for data processing, model deployment, and scaling. It consisted of the following courses:
-
Course 1: Browser-based Models with TensorFlow.js: Explored how to build and deploy machine learning models using TensorFlow.js, allowing for browser-based applications.
-
Course 2: Device-based Models with TensorFlow Lite: Learned how to optimize and deploy machine learning models on resource-constrained devices using TensorFlow Lite.
-
Course 3: Data Pipelines with TensorFlow Data Services: Covered techniques for building efficient data pipelines using TensorFlow Data Services (TFDS).
-
Course 4: Advanced Deployment Scenarios with TensorFlow: Explored advanced deployment scenarios, including model serving with TensorFlow Serving, cloud-based deployment on Google Cloud Platform, and scaling models with TensorFlow on multiple machines.