Use our Early Bird coupon code KTSPRING24 by January 5 to get 20% off your spring enrollment!

Deep Learning

[AI 2]

Full Course

$2021 USD
Before any discounts or coupons
for 18 hours

Class Package

Class Project(s)
1 project per half semester.
Virtual Machine (VM)
A Virtual Machine is a remote desktop that allows students to connect to it from anywhere. We provide VMs so that students use it during classes and to work on homework.
Student Progress Report
Students will get personalized progress reports and feedback from the instructor

Class Description:

Learn the most modern techniques for supervised learning, used in common applications such as facial recognition, speech recognition, and self driving cars. This course will also provide students with a linux server with GPU acceleration to run their algorithms. Topics include regression, test classification, convolutional image recognition, and more.


  • This course gives students access to professional research grade hardware, including compute servers such as a 16 core server with 128GB RAM, terabytes of fast storage, and research grade graphics processors such as the Titan X Pascal GPU
  • This course also teaches students how to use linux tools and the CUDA + GPU accelerated python research environment, using Tensorflow-GPU 1.4, Keras 2.1.4 - tools compiled with lubcudnn 6 and 7
  • Course material draws from recent academic research published in the last 2-5 years, including deep networks, single shot detection, convolutional or vectorizated models for language, as well as (time permitting) demo projects featuring AlphaZero Go and GAN inspired sequence to sequence learning.
When students move from [AI 1] to [AI 2], their focus shifts to getting the best possible model accuracies on real world data. Half the homework involves using pre-formatted data sets, while the second half involves students finding their own data sets. Students taking [AI 2] apply neural networks to text, images, and other data. Because the course is applied, much of [AI 2] involves the practice of parsing data and preparing it for use on research servers. This includes the mastery of linux command line tools, as well gaining a familiarity with different formats for data such as comma separated files, JSON APIs, and all sorts of image file types. Although the models are written in python, the class overall is language agnostic, as students pick up different tools to most effectively deal with different data. Indeed, students are expected to become proficient in the entire research lifecycle, from coming up to a hypothesis to explaining their model results.

This course no longer uses Theano, and students will model primarily with the Keras deep learning library backed by Tensorflow.

Research from KTBYTE students and alumni


Completion of [CORE 5b] or AP CS, or permission of instructor. Also requires Algebra II math experience. [AI 1] highly recommended but not required.

Related Classes

Sample Projects

These are examples of projects that students create as they grow their skills in [AI 2]

Post-Undergraduate / Research Grade Tools, Modeling with Keras and Tensorflow

Cutting edge techniques from resesarch in the last 2-5 years, e.g. Deep Convolutional Networks and Object Detection / Localization

GPU Compute Resources for Class include Titan Xp, GTX 1080ti, 32 Virtual Core Machine with 128GB RAM

Word Vectorization, Natural Language Classification, and broad coverage of different types of data sets

Linux tools, compute servers, provided in class. Students learn how to ask the right questions and perform research independently

Independent Student Projects can be submitted to science fairs or continued on in CS85


Introduction to Neural Networks

In this class we'll learn about the Perceptron as the building block for neural networks and deep learning

Introduction to TensorFlow

In this class we'll start exploring how to use the TensorFlow library.

More TensorFlow, Intro to Keras

In this class we'll keep working with TensorFlow and start learning to use Keras.

Working with Images

In this lesson we'll start learning how to process images with our ML architectures, including running a model for image ID or generation.

Convolutional Neural Networks (CNN)

Today we'll start exploring a new type of neural network and learn about regularizations

Transfer Learning

Transfer learning allows us to copy effective parts of existing models. Today we will also introduce the midterm project.

Midterm Project: Image Classification

Project Day

Finish Midterm Project, presentations

Students will present their work from the midterm project. Class discussion on topics to cover in Unit 2 in order to meet student goals.

Recurrent Neural Networks (RNNs)

RNNs can be used to make predictions about time series data, like words in a sentence. Topic may change depending on student goals for Unit 2.