MLx Fundamentals 24

This module delves into the intricacies of factorization algorithms, focusing on their pivotal role in recommender systems and deep learning. Students will explore metric factorization, low-rank methods, and their practical applications in optimizing deep learning processes. By understanding these concepts, learners will enhance their ability to implement efficient algorithms in real-world scenarios.

1. 1. Talk

In this module, students will explore foundational concepts of machine learning, including key algorithms, data preprocessing techniques, and evaluation metrics. This knowledge is essential for understanding how to build and assess machine learning models effectively.

1. 1. Factorisation methods in ML

In this module, students will explore foundational concepts of machine learning, including key terminology, methodologies, and applications. Through engaging video lectures, learners will gain insights into the principles that drive machine learning technologies and their relevance in various industries.

1. 1. Talk

In this module, students will explore foundational concepts of machine learning, including key terminology, methodologies, and applications. Through engaging video lectures, learners will gain insights into the principles that drive machine learning technologies and their relevance in various industries.

1. 1. Talk

In this module, students will explore essential machine learning concepts through hands-on applications of clustering and classification algorithms. Focusing on k-means clustering and naive Bayes classification, learners will gain insights into data understanding, feature engineering, and model evaluation techniques, equipping them with the skills to interpret and apply these models effectively.

1. 1. Talk

This module delves into the essential principles of optimization, equipping students with the knowledge to navigate complex algorithms and their applications in machine learning. Students will explore gradient descent, convex optimization, and the intricacies of non-convex functions, gaining insights into efficient problem-solving techniques that are crucial for developing robust machine learning models.

1. 1. Talk

In this module, students will explore essential optimization techniques for deep neural networks, focusing on gradient descent and hyperparameter tuning. Through hands-on coding exercises, learners will apply these concepts to real-world datasets like MNIST and CIFAR, enhancing their understanding of model training and performance optimization.

1. 1. Talk

In this module, students will delve into the essentials of generative AI and natural language processing. They will explore large language models, prompt engineering, and the role of language agents, gaining insights into their practical applications across various fields. This knowledge will empower students to enhance AI model performance and expand their understanding of AI technologies.

1. 1. Talk

In this module, students will delve into the practical applications of large language models and diffusion models. They will learn to connect to APIs, run models locally, fine-tune them, and generate images from text descriptions. Key concepts such as model inference, quantization, and effective prompting techniques will be explored, equipping students with the skills to enhance model efficiency and output quality.

1. 1. Talk

In this module, students will gain a solid understanding of fundamental machine learning concepts, including algorithms, regression, and the critical differences between traditional programming and machine learning. They will learn about the ordinary least squares algorithm, the significance of data in model training, and strategies to address overfitting and underfitting through regularization techniques.

1. 1. Talk