Coming Soon EE445/545: Image Analysis using Machine Learning:
Description: Computer Vision has become ubiquitous in our society, with applications in image understanding, mapping, medicine, drones, and self-driving cars. Visual recognition tasks such as image classification, localization and detection are core to these applications. Recent developments in neural network (aka “deep learning”) approaches have advanced the performance of these state-of-the-art visual recognition systems. This course will explore details of the deep learning architectures with a focus on learning end-to-end models for these tasks, particularly image classification. Students will learn to implement, train and debug their own neural networks on different machine vision tasks and gain a detailed understanding of research in computer vision. We will focus on teaching how to set up the problem of image recognition, the learning algorithms (e.g. backpropagation), practical engineering tricks for training and fine-tuning the networks and guide the students through hands-on assignments and a final course project.
Signals and Systems
All electrical engineering majors take EE 224, Signals and Systems I, typically as sophomores. The second course in the sequence EE 324, Signals and Systems II, is taken by most EE students as a technical elective as a second foundational course for specialization in signal processing, communications, and control systems. Both of the courses are four units with three hours of lecture, one hour of recitation and problem solving, and two hours of lab.
The specific learning objectives for Signals and Systems I are:
- Compute Fourier representations and plot spectra of signals.
- Manipulate signals and Linear Time Invariant (LTI)systems.
- Analyze LTI systems in time and frequency domains using convolution and frequency response.
- Demonstrate the processing of modulation and sampling in the time and frequency domains.
Taught:
Fall 2018 Syllabus
Fall 2017
EE224 Laboratory:
The current laboratory assignments are outdated and entirely software-based in Matlab and Simulink. This has led to the students focusing only on performing the necessary steps in the code rather than reflecting on what kinds of systems and signals are being analyzed and how they are analyzed. This fails to reinforce the core mathematical concepts of linear, time-invariant (LTI) systems and frequency analysis for fundamental engineering analysis. The labs are not adequately connecting concepts such as frequency domain analysis with earlier required courses in circuit design such as Electronic Circuits(EE 201) and Embedded Systems I(CprE 288).
Goal: This project will address the need for modern, compelling lab assignments in these key classes as well as connect the often abstract mathematics of complex exponentials with circuits and sensors that students have already been exposed to. Due to the complexity of integrating hardware into labs and training teaching assistants, most universities have defaulted to Matlab-only labs in signals and systems.
Taught:
Spring 2019
ECpE Senior Design Team SDMay18-31, Developing a New Lab Interface for EE224.
Systems Biology
Taught:
Spring 2019
Spring 2018