USC Viterbi Summer Undergraduate Research Experience (SURE)
Research Positions
Click on each project title to find a description of the lab and any preferred background. Many of these labs are interdisciplinary, so please look through all of them. here may also be Project Titles that have a primary major department, but are interdisciplinary and collaborate with other major departments, so feel free to look through all of the positions to find one that aligns with your interests.
We will be adding more labs during the upcoming weeks, so please come back to check out any additional labs that have been posted.
Faculty Name: Andreas Molisch
Faculty Department: Ming Hsieh Department of Electrical and Computer Engineering
Project Description: Deep neural networks have achieved outstanding success on many tasks in a supervised learning setting with enough labeled data. Yet, current AI systems are limited in understanding the world around us, as shown in a limited ability to transfer and generalize between tasks. The goal of the project is to investigate the machine learning-based wireless data augmentation and its possible application in the challenging city-level localization or to investigate how one can learn the optimal representation of wireless data from a reasonable set of assumptions as well as the experimental design of performing interventions (i.e., data interpolations) and acquiring labeled data efficiently. Work will entail designing, implementing, and evaluating machine learning-based fingerprinting-based outdoor localization in a wire-band wireless communication system under challenging environments, i.e., Non-line-of-sight (NLOS) radio propagation. Particular emphasis will be paid to the time series data augmentation and related data-efficient machine learning algorithms, one/few-shot learning, semi-supervised domain adaption, etc.
Related Background: EITHER good wireless communication background OR experience with common deep learning frameworks/software engineering skills, i.e., AT LEAST one of the following: 1. Wireless communication basics: Wireless signal propagation Mechanisms; Statistical Description of the Wireless Channel; Channel Models; 2. Programming experience in Python, Matlab, or Java; 3. Experience working in machine learning frameworks such as Pytorch, TensorFlow, or Keras.
Prerequisite: No formal pre-reqs, but see "related background" for required skills.
Faculty Name: Chia Hsu
Faculty Department: Ming Hsieh Department of Electrical and Computer Engineering
Website: https://sites.usc.edu/hsugroup/
Project Description: Maxwell's equations describe phenomena over the full electromagnetic spectrum from visible light to radio waves. Numerous problems, such as optical computing, metasurface design, inverse-scattering imaging, and stealth aircraft design, require computing the scattered wave given a very large number of distinct incident waves. However, existing Maxwell solvers scale poorly--either in computing time or in memory--with the number of input states of interest. The student will take part in our development of a new class of Maxwell solvers that can readily handle millions of distinct input states with orders-of-magnitude speed-up versus existing solvers.
Related Background: Programming experience. Familiarity with the differential form of Maxwell's equations (or wave equations in general).
Prerequisite: Programming; Maxwell's equations
Faculty Name: Chia Hsu
Faculty Department: Ming Hsieh Department of Electrical and Computer Engineering
Website: https://sites.usc.edu/hsugroup/
Project Description: We are developing computational imaging methods that can reconstruct volumetric 3D images even inside an opaque scattering medium that typically cannot be seen through. The student will take part in exploring different reconstruction algorithms, using experimental data that measured in our lab and using data computed from numerical simulations.
Related Background: Able to code and to debug with MATLAB. Knowledge of wave equations.
Prerequisite: Familiar with MATLAB
Faculty Name: Chia Hsu
Faculty Department: Ming Hsieh Department of Electrical and Computer Engineering
Website: https://sites.usc.edu/hsugroup/
Project Description: We are developing imaging methods that can reconstruct volumetric 3D images even inside an opaque scattering medium that typically cannot be seen through. The student will take part in building the experimental setup, data acquisition, instrument automation and calibration, and sample preparation.
Related Background: Optics experiment experience
Prerequisite: Optics experiment experience
Faculty Name: Chia Hsu
Faculty Department: Ming Hsieh Department of Electrical and Computer Engineering
Website: https://sites.usc.edu/hsugroup/
Project Description: "Exceptional points" are unique states where two optical modes coalesce into one mode. Lasers operating near exceptional points exhibit enhanced sensitivity to perturbations, making them promising as ultra-sensitive sensing devices such as gyroscopes. However, lasers operating near exceptional points also exhibit complex nonlinear dynamics, which affect the noise properties and the signal-to-noise ratio of the sensor. In this work, the student will work with a PhD student on the theoretical/numerical modeling of the nonlinear dynamics and noise properties of such unique lasers by numerically integrating coupled nonlinear ordinary differential equations.
Related Background: Familiar with differential equations. Programming experience
Faculty Name: David Barnhart
Faculty Department: Information Sciences Institute
Website: https://leapfrog.isi.edu/
Project Description: LEAPFROG is a standalone lunar lander prototype vehicle that uses an RC turbine engine and paintball tanks to fly repeatedly to test in simulated lunar landing conditions.
Related Background: EE, MechE, CS, AE
Prerequisite: Some hands on EE experience, GNC knowledge
Faculty Name: David Barnhart
Faculty Department: Information Sciences Institute
Project Description: CLING-ERS is a genderless docking system that has gotten approval to be tested onboard the ISS in the summer of 2022.
Related Background: EE, ME, AE, CS
Prerequisite: Some hands on EE experience, RTOS programming (C or Python)
Faculty Name: David Barnhart
Faculty Department: Information Sciences Institute
Project Description: STARFISH is a unique robotic system meant to operate in space and uses a completely soft flexible material and distributed processing to operate very similar to a biological starfish does.
Related Background: EE, CS, AE with Controls background
Prerequisite: Some hands on EE experience, RTOS programming (C or Python), 3D printing experience
Faculty Name: Ellis Meng
Faculty Department: Biomedical Engineering
Project Description: Implantable medical microdevices enable exciting possibilities such as communicating with neurons and monitoring disease conditions inside the body. Many of these devices rely on specialized thin-film polymers to electrically insulate them from fluids and tissues. However, the harsh environment inside the body can affect this insulation and cause the devices to fail. This project will involve making samples of specialized polymers in a microfabrication cleanroom, subjecting the samples to a simulated in vivo environment, and measuring their insulating qualities over time. The findings will tell researchers and engineers how they can best make implantable medical microdevices so that performance inside the body is reliable and long-lasting.
Related Background: N/A
Prerequisite: Enrolled in engineeering, applied physics, physics, or related undergraduate program
Faculty Name: Heather Culbertson
Faculty Department: Computer Science
Website: https://sites.usc.edu/culbertson/
Project Description: This project focuses on the design, building, and control of haptic devices for virtual reality. Current VR systems lack any touch feedback, providing only visual and auditory information to the user. However, touch is a critical component for our interactions with the physical world and with other people. This research will investigate how we use our sense of touch to communicate with the physical world and use this knowledge to design haptic devices and rendering systems that allow users to interact with and communicate through the virtual world. To accomplish this, the project will integrate electronics, mechanical design, programming, and human perception to build and program a device to display artificial touch sensations to a user with the goal of creating a natural and realistic interaction.
Related Background: Background in computer science, electrical engineering, mechanical engineering, or related majors. Experience with circuits and mechanical design a plus, but not required.
Prerequisite: Programming experience (C++ preferred)
Faculty Name: Jesse Thomason
Faculty Department: Computer Science
Website: https://jessethomason.com/
Project Description: An agent interpreting natural language instructions in a real or simulated world needs to identify salient objects in the world to which that language refers. Many methods for benchmarks like ALFRED [https://askforalfred.com/] use off-the-shelf object detectors like Faster R-CNN, minimally fine-tuning them for objects in the 3D environment. We hypothesize that understanding what kind of object an agent is looking for can influence the accuracy of object detections. For example, a detector trained specifically to recognize "pickupable" objects will more likely detect small objects like forks and spoons, one for "openable" objects cabinet and drawer faces, and one for "closable" objects cabinet and drawer interiors. The project will involve using action types as conditioning information for object detectors in a language-guided task completion benchmark. The student will become familiar with the ALFRED benchmark and with one or more state of the art models that tackle the challenge. We will aim to achieve a new state of the art by adding action-conditioned visual object recognition.
Related Background: Should be comfortable programing in python. Familiarity with pytorch would be a plus.
Prerequisite: CSCI 360 or CSCI 467
Faculty Name: Mayank Kejriwal
Faculty Department: Information Sciences Institute
Website: https://usc-isi-i2.github.io/ai-networks-society/
Project Description: AI, Networks and Society is a multi-year collection of projects in our group that seeks to use various sources of data to learn more about society using data-driven tools and frameworks, including machine learning and AI. By drawing on an empirically rigorous methodology, we seek to study complex systems in domains such as elections, social media, health and finance. Individual projects are often published in top-tier journals and conferences, and some have received widespread press coverage, including in Popular Science and San Francisco Times.
Related Background: A course in probability & statistics is preferred, and some background in AI or machine learning (whether applied or through coursework) is preferred as well.
Prerequisite: Introductory programming courses, including data structures
Faculty Name: Meisam Razaviyayn
Faculty Department: Daniel J. Epstein Department of Industrial and Systems Engineering
Website: https://sites.usc.edu/razaviyayn/
Project Description: The goal of this project is to train neural networks using measures of performance other than accuracy in the presence of content-shifts. This is particularly important in applications such as classification of hateful/misinformation posts on social media platforms. In this application, the number of positive samples (sample posts containing misinformation) is small compared to the entire number of samples. Hence non-decomposable measures of performance, such as AUROC or accuracy at the top, are needed for auto-enforcement of the integrity-related policies on social media platforms. However, these measures of performance are vulnerable to content shifts. Our goal is to develop scalable algorithms for training neural networks based on measures of performance related to accuracy at the top. Furthermore, the resulting model needs to be robust against content-shifts. This is because the topic of misinformation changes over social media platforms over time.
Related Background: Basic knowledge of machine learning and neural networks. Being familiar with PyTorch and TensorFlow.
Prerequisite: Machine Learning, PyTorch, TensorFlow
Faculty Name: Muhao Chen
Faculty Department: Information Sciences Institute
Website: https://luka-group.github.io/research.html
Project Description: Knowledge acquisition (e.g., relation extraction, entity and event typing) faces challenges including extreme label spaces, few-shot/zero-shot predictions and out-of-domain prediction. To this end, we study methods for leveraging indirect supervision signals from auxiliary tasks (e.g., natural language inference, text summarization, etx.) to foster robust and generalizable inference for knowledge acquisition. In the same context, we study methods for generating semantically rich label representations based on either gloss knowledge or structural knowledge from a well-populated lexical knowledge base, in order to better support learning with limited labels. This project is to target publication(s) in top-tier ML/NLP conferences or journals.
Related Background: proficiency in pytorch and huggingface
Prerequisite: solid background in NLP or machine learning (deep learning), proficiency in PyTorch and Hugging Face
Faculty Name: Muhao Chen
Faculty Department: Information Sciences Institute
Website: https://luka-group.github.io/research.html
Project Description: Human languages evolve to communicate about events happening in the real world. Therefore, understanding events plays a critical role in natural language understanding (NLU). A key challenge to this mission lies in the fact that events are not just simple, standalone predicates. Rather, they are often described at different granularities, temporally form event processes, and are directed by specific central goals in a context. Our research in this line helps the machine understand events described in natural language. This includes the understanding of how events are connected, form processes or structure complices, and the recognition of typical properties of events (e.g., space, time, salience, essentiality, implicitness, memberships, etc.). This project is to target publication(s) in top-tier ML/NLP conferences or journals.
Related Background: solid background in NLP or machine learning (deep learning), proficiency in PyTorch and Hugging Face
Prerequisite: solid background in NLP or machine learning (deep learning)
Faculty Name: Muhao Chen
Faculty Department: Information Sciences Institute
Website: https://luka-group.github.io/research.html
Project Description: Knowledge graphs (KGs) provide both open-world and domain-specific knowledge representations that are integral to many AI systems. However, constructing KGs is usually very costly and requires extensive effort. A widely attempted solution is to learn knowledge acquisition models that automatically induce structured knowledge from unstructured text. However, such models developed through data-driven machine learning are usually fragile to noise in learning resources, and may fall short of providing reliable inference on large, heterogeneous real-world data. We are developing a general meta-learning framework that seeks to systematically improve the robustness of learning and inference for data-driven knowledge acquisition models. We seek to solve several key problems to accomplish the goal: (i) How to identify incorrect training labels and prevents overfitting on noisy labels; (ii) how do detect invalid input instances in inference (e.g., out-of-distribution ones) and provide abstention-awareness; (iii) automated constraint learning that strengthens model inference with global consistency; (iv) how to automatically augment training signals of the knowledge acquistion model or the backbone language model. This project is to target publication(s) in top-tier ML/NLP conferences or journals.
Related Background: solid background in NLP or machine learning (deep learning), proficiency in PyTorch and Hugging Face
Prerequisite: solid background in NLP or machine learning (deep learning)
Faculty Name: Peter Beerel
Faculty Department: Ming Hsieh Department of Electrical and Computer Engineering
Website: https://sites.usc.edu/eessc/
Project Description: This project goal is to develop energy-efficient multi-object detection and tracking models for autonomous driving applications. In particular, we are exploring downsampling/compression techniques that can aggressively reduce the size of the activation maps early in the object detection/tracking network (eg. Faster R-CNN, YOLOvx), such as dynamic neural networks, early exits, etc.
Related Background: N/A.
Prerequisite: The student should be familiar with ML frameworks, such as Pytorch/Tensorflow/MXNet and is preferred to have some background in object detection.
Faculty Name: Quan Nguyen
Faculty Department: Aerospace and Mechanical Engineering
Website: https://sites.usc.edu/quann/
Project Description: Design and Control of a Highly Dynamic Wheel-legged Robot. A video of the current result can be seen at: https://youtu.be/9vkS0IoGp0s
Related Background: Computer Science, Mechanical Engineering, Electrical Engineering
Prerequisite: Background in Design, Control, Robotics
Faculty Name: Shaama Sharada
Faculty Department: The Mork Family Department of Chemical Engineering and Materials Science
Website: https://sharada-lab.usc.edu/
Project Description: While manmade processes for conversion of natural gas resources to useful products require extreme temperatures and pressures and lots of energy, enzymes found in bacteria can carry out highly selective transformations under ambient, mild conditions. Our goal is to demystify these processes and uncover new catalysts using clever quantum chemical strategies for probing mechanisms and predicting catalyst compositions.
Related Background: Some experience with quantum chemical/molecular dynamics simulations desirable
Prerequisite: Kinetics
Faculty Name: Shaama Sharada
Faculty Department: The Mork Family Department of Chemical Engineering and Materials Science
Website: https://sharada-lab.usc.edu/
Project Description: While machine learning methods are rapidly and successfully being adopted for predicting material and chemical properties, the inverse problem of predicting novel materials with desired properties is still in its infancy. We are implementing deep learning frameworks to address this problem and to explore the chemical space based on electronic and steric properties of ligands in transition metal complex catalysts.
Related Background: Introductory machine learning course desirable
Prerequisite: Python/programming
Faculty Name: Shaama Sharada
Faculty Department: The Mork Family Department of Chemical Engineering and Materials Science
Website: https://sharada-lab.usc.edu/
Project Description: Supported single atom catalysts are touted as being highly efficient and economical compared to supported precious metal nanoparticle catalysts. However, the activity and stability are dependent on operating conditions and reactants/products involved. We use quantum chemical and dynamics approaches to probe these dependencies and design catalysts for various applications including preferential oxidation for fuel cell feed.
Related Background: Some prior experience with quantum chemistry/molecular dynamics simulations desirable
Prerequisite: Kinetics
Faculty Name: Somil Bansal
Faculty Department: Ming Hsieh Department of Electrical and Computer Engineering
Website: https://smlbansal.github.io/LB-WayPtNav/
Project Description: Autonomous robot navigation is a fundamental and well-studied problems in robotics. However, developing a fully autonomous robot that can navigate in a priori unknown environments is difficult due to challenges that span dynamics modeling, on-board perception, localization and mapping, trajectory generation, and optimal control. Classical approaches such as the generation of a real-time globally consistent geometric map of the environment are computationally expensive and confounded by texture-less, transparent or shiny objects, or strong ambient lighting. End-to-end learning can avoid map building, but is sample inefficient. Furthermore, end-to-end models tend to be system-specific. In this project, we will explore modular architectures to operate autonomous systems in completely novel environments using the onboard perception sensors. These architectures use machine learning for high-level planning based on the perceptual information; this high-level plan is then used for low-level planning and control via leveraging classical control-theoretic approaches. This modular approach enables the conjoining of the best of both worlds: autonomous systems learn navigation cues without extensive geometric information, making the model relatively lightweight; the inclusion of the physical system structure in learning reduces sample complexity relative to pure learning approaches. Our preliminary results indicate a 10x improvement in sample complexity for wheeled ground robots. Our hypothesis is that this gap will only increase further as the system dynamics become more complex, such as for an aerial or a legged robot, opening up new avenues for learning navigation policies in robotics. Preliminary experiment videos can be found at: https://smlbansal.github.io/LB-WayPtNav/ and https://smlbansal.github.io/LB-WayPtNav-DH/.
Related Background: Experience and background (if any) in ML, control, and/or robotics. Experience (if any) with MATLAB/Python, training deep networks, ROS, and/or working with real hardware. Note that experience is not strictly necessary.
Prerequisite: N/A
Faculty Name: Somil Bansal
Faculty Department: Ming Hsieh Department of Electrical and Computer Engineering
Website: https://smlbansal.github.io/website-safe-navigation/
Project Description: Machine learning-driven vision and perception components make a core part of the navigation and autonomy stacks for modern robotic systems. On the one hand, they enable robots to make intelligent decisions in cluttered and a priori unknown environments based on what they see. On the other hand, the lack of reliable tools to analyze the failures of learning-based vision models make it challenging to integrate them into safety-critical robotic systems, such as autonomous cars and aerial vehicles. In this project, we will explore a robust control-based safety monitor for visual navigation and mobility in unknown environments. Our hypothesis is that rather than directly reasoning about the accuracy of the individual vision components and their effect on the robot safety, we can design a safety monitor for the overall system. This monitor detects safety-critical failures in the overall navigation stack (e.g., due to a vision component itself or its interaction with the downstream components) and provides safe corrective action if necessary. The latter is more tractable because the safety analysis of the overall system can be performed in the state-space of the system, which is generally much lower dimensional than the high-dimensional raw sensory observations. A key characteristic of our framework is that since the robot is operating in an unknown environment, the safety monitor itself is updated online as new observations are obtained. Preliminary results on simulated and real robots demonstrate that our framework can ensure robot safety in various environments despite the vision component errors (the videos can be found at https://smlbansal.github.io/website-safe-navigation/). Other than ensuring robot safety, we also propose using our framework to mine the critical failures at scale and improve the robot perception over time.
Related Background: - Experience and background (if any) in control and/or robotics. - Experience (if any) with programming in MATLAB/Python, ROS, and/or working with real hardware. Note that experience is not necessary, but knowing your background can help with finding a fit.
Prerequisite: N/A
Faculty Name: Sze-Chuan Suen
Faculty Department: Daniel J. Epstein Department of Industrial and Systems Engineering
Project Description: We have recently developed and validated a model to predict need for massive transfusion (MT) using modern machine learning (ML) methods. MT may be needed when an injured patient enters the trauma center, and MT protocols require blood for transfusion to be supplied from inventory. Accurate prediction of the need for MT may reduce delays and unnecessary inventory requests. We are now working on building a user-friendly online interface to help physicians use our ML method in emergency settings. This may require simplification of the model to fewer variables, as well as developing methods to increase usability of the interface (layout design, etc.).
Related Background: Experience with usability studies, design of websites/interfaces
Prerequisite: Experience working with data (machine learning experience welcomed)
Faculty Name: Jayakanth Ravichandran
Website: http://alchemy.usc.edu
Project Description: We are exploring a novel class of semiconductors with large density of states (high absorption coefficient and carrier density) with tunable structure and composition. We have already demonstrated materials with a world record high birefringence (different refractive index along the optic axis and other principal axis) and properties suitable photovoltaic applications. We use crystal growth to produce high quality materials for these investigations. We are expanding our efforts to thin film growth of these materials now.
Related Background: Candidates will have a background in materials science, physics, chemistry, or related engineering disciplines. Coursework in thermodynamics and solid state physics is typically helpful.
Prerequisite: Basic Materials science related classes (Physics/Chemistry/Engineering)
Faculty Name: Daniel McCurry
Website: https://www.mccurrylab.com/
Project Description: Despite >100 years of drinking water disinfection, the environmental engineerin ‘toolbox’ contains only six commonly used chemical disinfectants, which are also often used for oxidation of trace organic contaminants. Among the dozens of oxidants employed by chemists, most are unsuitable for drinking water treatment, due to their cost or toxicity. However, one promising option could be the application of Group 10 metal (e.g., Pt, Pd) catalysts to oxidize molecules while using dissolved oxygen as the terminal electron acceptor. Oxidation of alcohols to aldehydes and oxygenation of alkanes have all be demonstrated under mild conditions (room temperature water) with Pt and/or Pd on the surface of solid supporters. Dissolved oxygen is typically present in surface waters near its solubility (8 mg/L), which is approximately five to ten times higher than the molar concentration of chlorine typically used for water disinfection. This research aims to identify new, safe, and sustainable oxidation technologies, informed by an organic chemistry perspective. The student on this project would specifically be assisting a PhD student in performing experiments on oxidation of trace aldehydes (e.g., acetaldehyde) in recycled wastewater. Day-to-day tasks would involve setting up batch reactor and column experiments, and doing analytical chemistry (e.g., HPLC, GC/MS) to measure the concentrations of reactants, intermediates, and products
Related Background: Organic chemistry and any additional laboratory experience is helpful.
Prerequisite: Year of general chemistry
Faculty Name: Alejandra Uranga
Faculty Department: Aerospace and Mechanical Engineering
Project Description: This project will be carried out in the Dryden Wind Tunnel as part of the Aerodynamic Design & Research Lab (ADRL) of Prof. Uranga. The goal of the work will be to help perform experimental wind tunnel testing of advanced aerodynamic configurations, as well as assisting with general tasks related to the wind tunnel and its new test section. This might include designing and manufacturing of test models, setting up testing equipment, running test, and processing and interpretation data.
Related Background: Some knowledge of fluid mechanics, mechanical design, and/or experimental testing
Prerequisite: Aerospace or Mechanical Engineering undergraduate
Faculty Name: Andrea Armani
Faculty Department: The Mork Family Department of Chemical Engineering and Materials Science
Website: https://armani.usc.edu/
Project Description: The over-arching mission of the research group is to develop novel nonlinear materials and integrated optical devices that can be used in understanding disease progression and in quantum optics. As part of these efforts, we have numerous collaborations in tool and technology development to enable research and discovery across a wide range of fields. This work combines many topics including organic and inorganic materials synthesis, nonlinear optics and integrated photonics, and cell/tissue biology. As a result of the multi-disciplinary nature of the research being pursued in the Armani group, undergraduate research projects are tailored to the undergraduate researcher's interests within the general scope of the research activities of lab. Example projects being pursued in the Armani Lab by undergraduate researchers include the synthesis of nanoparticles and polymers and fabrication of integrated optical devices. In developing a project, the student's academic background, prior research experience, and areas of interest are balanced.
Related Background: Degree in STEM field
Prerequisite: none
Faculty Name: Peter Beerel
Faculty Department: The Mork Family Department of Chemical Engineering and Materials Science
Website: https://sites.usc.edu/eessc/research-areas/interdisciplinary-research/
Project Description: California wildfires have, in 2020 alone, burned over 4 million acres, damaged or destroyed more than 10000 buildings, and caused more than 30 fatalities. The destructive impact of these fires is projected to only worsen unless innovative solutions are researched, demonstrated, commercialized, and adopted. Our group’s vision is to build a collaborative team of researchers to leverage the massive advances in machine learning and drone technologies and build a network of drones for wildfire detection and fighting. The objective of the system is to automatically detect a wildfire within the first ~5 minutes of its creation and extinguish it before it grows over ~0.5 acres in size and perform structure protection by detecting, tracking, and following embers.
Related Background: Background on ML
Prerequisite: Object detection and tracking experience desired.
Faculty Name: Vatsal Sharan
Faculty Department: Computer Science
Website: https://vatsalsharan.github.io/
Project Description: The student will explore foundational questions regarding machine learning, using a combination of systematic experiments and theoretical analysis. Both students interested in performing systematic experiments to tease out phenomenon in practice, and those interested in using theoretical tools to prove novel guarantees are welcome. The exact questions and their scope is broad, but the following are some potential options: 1. Understanding deep learning: One particular question of interest here is to understand why neural networks generalize despite having the capacity to overfit. We've been exploring what role the data itself has to play in this mystery, exploring connections to the amazing self-supervised learning capability of neural networks in the process. 2. Data augmentation and amplification: In some recent work ("Sample Amplification"), we showed that it is often possible to generate new samples from a distribution without even learning it. We will explore how this ties into various data augmentation techniques, and develop new frameworks to increase dataset size. 3. Fairness and robustness: We will explore how to train models which are robust in many ways, such as to changes in the data distribution, or to do well on minority sub-populations (and not just on average over the entire data). 4. Computational-statistical tradeoffs: This is a more theoretical direction, to understand when computational efficiency might be at odds with statistical requirements (the data needed to learn). Recent work has opened by much uncharted territory, particularly with respect to the role of memory in learning, which we will explore.
Related Background: Some basic understanding of machine learning would be very helpful for certain projects.
Prerequisite: Familiarity with probability, linear algebra, calculus, and analysis of algorithms.
Faculty Name: Constantine Sideris
Faculty Department: Ming Hsieh Department of Electrical and Computer Engineering
Website: http://sites.usc.edu/acmelab/
Project Description: The student will assist with the design, simulation, and implementation of integrated CMOS biosensors for Point-of-Care diagnostic applications. The goals are to develop rapid, at-home diagnostics for early detection and prevention of disease. The project will involve direct work with circuit simulation and design tools, as well as printed circuit board (PCB) design software.
Related Background: Prospective students should have some background in analog circuits, electromagnetics, and PCB design experience. Students applying for this project should ideally be at the junior or senior level.
Prerequisite: Analog circuits, electromagnetics
Faculty Name: Constantine Sideris
Faculty Department: Ming Hsieh Department of Electrical and Computer Engineering
Website: http://sites.usc.edu/acmelab/
Project Description: The student will assist with the design, simulation, and implementation of integrated CMOS biosensors for Point-of-Care diagnostic applications. The goals are to develop rapid, at-home diagnostics for early detection and prevention of disease. The project will involve direct work with circuit simulation and design tools, as well as printed circuit board (PCB) design software.
Related Background: Prospective students should have some background in analog circuits, electromagnetics, and PCB design experience. Students applying for this project should ideally be at the junior or senior level.
Prerequisite: Analog circuits, electromagnetics
Faculty Name: Feifei Qian
Faculty Department: Ming Hsieh Department of Electrical and Computer Engineering
Website: https://minghsiehece.usc.edu/directory/faculty/profile/?lname=Qian&fname=Feifei
Project Description: The selected candidate will work closely with our research group to support our mission in (1) understanding the mechanism of robot interaction with obstacles, and (2) creating innovative strategies for robots to take advantage of obstacle interactions to navigate in complex environments with minimal control effort In this role, the candidate will perform the following tasks: program simple robot gaits; perform systematic experiments to test performance of different gaits during obstacle negotiation; use MATLAB to perform simple analysis and create plots to communicate results; (optional) develop simple algorithms to adapt gaits through different environments.
Related Background: Sophomore or above, with major in Electrical Engineering, Mechanical Engineering, physics, or related areas; Experience with Solidworks, MATLAB, and C++ is desired; Experience with robotics is a plus
Prerequisite: Intro physics, basic programming, mechanical design
Faculty Name: Feifei Qian
Faculty Department: Ming Hsieh Department of Electrical and Computer Engineering
Website: https://sites.google.com/usc.edu/roboland/
Project Description: The selected candidate will work closely with Dr. Feifei Qian's group to support our mission in (1) develop high-mobility legged robots with embodied sensing capabilities, to help human scientists in exploration of complex natural environments such as deserts, forests, and muddy terrains; (2) enable the robot to infer human exploration objectives and aid human experts with adaptation of sampling strategies in response to incoming information. In this role, the candidate will perform the following tasks: design and control multi-legged robots for sand and mud traversal; perform systematic experiments to characterize robot leg force sensing capabilities and measure terrain reaction forces; use MATLAB to perform simple analysis and create plots to communicate results; develop simple algorithms for robot to suggest sampling strategies to humans and get feedback.
Related Background: mechanical engineering, electrical engineering, computer science, physics, or other related majors
Prerequisite: SolidWorks, programming, microcontroller-related experiences, basic physics