
Advanced Machine Learning for High-Schoolers
Take Your Machine Learning Skills to the Next Level: Explore AI, Neural Networks, and NLP
Building on the classes in the 3-course Machine Learning series, Advanced Machine Learning digs deeper into advanced neural networks and natural language processing. Courses will cover such topics as Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), and Radial Basis Function Networks (RBFNs), while also examining their use in tasks like classification, image processing, and data generation. Students will also gain a comprehensive introduction to Natural Language Processing (NLP), sequence modeling with Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) architectures.
Learning Format:
Online | 3 - 9 Months
Enjoy the flexibility of learning at your own pace while the course is open. Courses are 100 percent online, with no in-person meetings. You will have access to the course materials for about 3-weeks per course during the Summer quarter and about 10-weeks per course during the Fall, Winter, and Spring quarters.
What you will learn:
- Review the Deep Neural Network (DNN) framework (i.e. “DNN framework”) developed in the Futures Machine Learning series (Course 3).
- Apply the DNN framework to complex classification projects.
- Design, implement, integrate, and test a Convolutional Neural Network (CNN) class into DNN framework.
- Design, implement, integrate, and test a Radial Basis Function Network (RBFN) class into the DNN framework.
- Design and implement a Generative Adversarial Networks (GANs) and apply it to data generation.
- Design and implement a sentiment analysis application utilizing a natural language toolkit (nltk).
- Parts of Speech (PoS) and PoS tagging as it applies to identifying grammatical tags in text.
- Tokenization, stemming, and lemmatization text processing in NLP.
- Representing words as multi-dimensional vectors using word embeddings.
- Sequence prediction using Recurrent Neural Networks (RNNs).
- RNN shortcomings and enhancements on sequence prediction with Long Short Term Memory (LSTM) networks.
- Review of Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) models for processing and predicting sequential data.
- Introduction to Transformers and applications to sequential data processing.
- Introduction to Attention and integration with NLP transformer models.
- Introduction to Generative Pretrained Transformers (GPT) and Bidirectional Encoder Representations from Transformers (BERT) for text generation and sentiment analysis.
How to Enroll:
Pay as You Go Per Course:
For general enrollments, expand the “courses” tab at the bottom of this page to review the course list and then click a course to see details and enroll. You may pay per course as you work through the program. Courses must be taken in sequence.
Scholarships:
No Futures scholarships are available for Fall 2025.