AV俱乐部

I am looking for up to 3 students for 3 projects. Project 1 focuses on exploiting width measures similar to treewidth to obtain efficient algorithms for constructing phylogenetic networks. Project 2 focuses on proving lower bounds that establish that some of the algorithms for phylogenetic network construction problems that have been developed so far are optimal. Project 3 focuses on constructing networks belonging to particular classes more efficiently, and on recognizing networks that belong to these classes.

Accepting: PhD students

 in working with Dr. Norbet Zeh.

I am leading a project funded through the Transforming Climate Action network in the area of environmental DNA (eDNA) analysis. eDNA is a powerful proxy for the diversity of life in the ocean, and a single drop of seawater can tell us about all the organisms that can be found in that part of the ocean. New sampling and sensing devices are being deployed that can do DNA sequencing in situ, but doing so will require efficient algorithms and carefully designed databases to minimize power consumption on devices with minimal battery life.

Accepting: PhD students

 in working with Dr. Robert Beiko.

This research project investigates the convergence of artificial intelligence, intellectual property law, and ethical considerations in modern animal agriculture. By developing advanced AI models to monitor and interpret livestock behavior and health, the project aims to enhance animal welfare and promote sustainable farming practices. It explores the legal implications surrounding data ownership and intellectual property rights of AI algorithms used in animal care. Ethical issues such as privacy, consent, and the impact of technology on farmers and animals are central to the study. The goal is to create a framework that balances technological innovation with legal and ethical responsibilities, advancing both animal welfare and the agricultural industry.

Accepting: PhD and MCS students

 in working with Dr. Suresh Neethirajan.

This research project aims to integrate the traditional knowledge and practices of the Mi'kmaq and other First Nations communities within Nova Scotia with advanced artificial intelligence technologies to improve animal welfare. By actively learning from these Indigenous communities, the project seeks to understand their deep-rooted insights into animal behavior, ethical treatment, and sustainable farming practices. These invaluable perspectives will guide the design and implementation of AI technologies鈥攕uch as ML models for monitoring livestock health and well-being鈥攖o create solutions that are both culturally respectful and technologically innovative. The goal is to harmonize ancestral wisdom with modern digital tools, enhancing animal welfare while fostering sustainable agriculture. Central to the study are ethical considerations, community engagement, and the co-creation of knowledge, bridging traditional practices with cutting-edge technology for the betterment of animals and farming communities alike.

Accepting: PhD and MCS students

 in working with Dr. Suresh Neethirajan.

This research project focuses on leveraging artificial intelligence and big data to transform dairy and poultry farming practices with the goal of reducing greenhouse gas (GHG) emissions and achieving net-zero targets. By integrating AI-driven analytics, machine learning models, and precision agriculture technologies, the project aims to optimize feed efficiency, improve animal health monitoring, and enhance waste management systems. The study will analyze large datasets collected from digital livestock farming operations to identify patterns and develop predictive models that support sustainable decision-making. The ultimate goal is to create innovative, climate-smart farming methods that not only enhance productivity and animal welfare but also significantly cut down GHG emissions.

Accepting: PhD and MCS students

 in working with Dr. Suresh Neethirajan.

Map Perception as Program Synthesis

Current AI models formalize planning as a search in a decision tree of potential actions and outcomes. The size of this tree determines the computational cost of the problem, or its theoretical difficulty. However, theoretical difficulty rarely aligns with human experience, as people often easily solve problems deemed intractable in theory. The key characteristic of real-world problems that people are so adept at is their compositional, semi-regular structure, such as predictable patterns of hills and valleys in nature, or structured street networks in built environments. Computational study of how people plan in such contexts is central to engineering resource-efficient AI that can plan with human-like efficiency, while adapting to increasing problem scales. In this project, we will integrate AI, Large Language Models, and psychology in new ways to develop a computational understanding of how people conceptualize maps and plan in realistic spatial navigation tasks. We will build computational models that can anticipate environmental structure and create human-like AI that can produce efficient plans in realistic domains.

Accepting: PhD students

 in working with Dr. Marta Kryven. 

Existing cognitive models of planning (e.g., in games like chess) tend to pre-specify possible planning models as anchored to classic algorithms, such as MDP solvers and stochastic search. In contrast, people likely maintain and learn an evolving library of planning strategies encoded as mental programs, and grow this library through experience. In this project, we explore approaches to modeling how such libraries of programs evolve and grow through social interaction and experience. We will work in collaboration with cognitive and developmental psychologists to build AI that can grow and learn like a child.

Accepting: PhD students

 in working with Dr. Marta Kryven. 

Genetic programming (GP) provides an approach to reinforcement learning in which the representation and parameters are both optimized. Moreover, there is no need to assume that the reward function need be differentiable. This may lead to solutions that are particularly sparse/interpretable/computationally efficient and/or uniquely reflect the objectives of the task domain. However, the representation is not purely numerical, thus genetic programming also typically makes limited use of local rewards and is therefore not sample efficient under reinforcement learning (RL) tasks. With this in mind, this project will investigate aspects of diversity maintenance, competitive coevolution, offline RL and state space priors.

Accepting: PhD students

 in working with Dr. Malcolm Heywood.

With a few exceptions, current applications of deep RL have been limited to tasks that can be accurately simulated, like board and video games. One reason for this limitation is that current deep RL methods are data-inefficient, requiring large amounts of interaction data to learn, which can be expensive and time-consuming to gather in the real world. I am looking for students who would be interested in working with me to develop methods that would improve the data efficiency of deep RL agents and thereby facilitate the successful application of RL to a wider range of real-world tasks.

If you are interested in working with me, please refer to the 'Prospective Students' page on my website for more information and instructions on how to apply. 

Accepting: Phd students

 in working with Dr. Janarthanan Rajendran.

• Passive sensing and ubicomp for tracking and screening cognitive developmental milestones. We will explore the use and fabrication of ubicomp for passive sensing in the home setting.
• Enhancing reading and writing skills of children at school. We will explore how to improve literacy skills of children considering cultural aspects.
• Ubicomp supporting adults with autism manage anxiety and stress in real-life situations.

Accepting: PhD students

 in working with Dr. Lizbeth Olivia Escobedo Bravo.

Existing cognitive models of planning (e.g., in games like chess) tend to pre-specify possible planning models as anchored to classic algorithms, such as MDP solvers and stochastic search. In contrast, people likely maintain and learn an evolving library of planning strategies encoded as mental programs, and grow this library through experience. In this project, we explore approaches to modeling how such libraries of programs evolve and grow through social interaction and experience. We will work in collaboration with cognitive and developmental psychologists to build AI that can grow and learn like a child.

Accepting: PhD and MCS students

 in working with Dr. Nils Wilde

Accepting: PhD students

 in working with Dr. Hanieh Shakeri.

This research project aims to enhance the welfare of dairy cattle by developing innovative digital interfaces that facilitate better human-computer-animal interactions. By integrating artificial intelligence technologies such as machine learning, facial recognition, and natural language processing, the project seeks to interpret cows' behaviors and vocalizations to understand their health and emotional states more accurately. It involves creating user-friendly platforms for farmers to monitor real-time data on livestock well-being, enabling timely interventions and improving overall farm productivity. Ethical considerations, including data privacy and the impact of technology on both animals and farmers, are central to the study. The ultimate goal is to promote sustainable and ethical farming practices by bridging the communication gap between humans and dairy animals through advanced technological solutions.

Accepting: PhD and MCS students

 in working with Dr. Suresh Neethirajan.

Persuasive systems are interactive systems (such as mobile, web, virtual reality, and augmented reality apps and games) designed to promote desirable behaviours or discourage risky behaviours without coercion or deception. My research intersects Human-Computer Interaction, Artificial Intelligence (AI), and Persuasive Computing to design, develop, and evaluate next-generation persuasive systems that are AI-powered, highly personalized, user-adaptive, and more effective at motivating and promoting desirable behaviours in individuals and groups across diverse health domains including disease prevention and management, physical activity, and mental health.

I am looking for candidates with strong background in software development and AI techniques including machine learning, deep learning, and natural language processing. Past experience with research and development projects involving building and deploying AI models, along with developing interactive systems that integrate these models, is a plus.

Accepting: PhD and MCS students

 in working with Dr. Oladapo Oyebode.

My research focuses on the intersection of graphics, AI and interaction and, importantly, includes the concurrent goal of developing new and accessible graphics methods. These initiatives feed directly into my long-term research trajectory which aims to infuse novel graphics methods with perceptual and aesthetic elements. Ongoing topics of interest include high dynamic range graphics, navigation through virtual worlds and the structured presentation of 3D models.

Accepting: PhD students

 in working with Dr. Stephen Brooks.

I want PhD/MCS students interested in designing the new wave of 3D user interfaces for VR/AR for creative tasks. The 3DUI can utilize ML as a base to simplify a task, utilize multimodal interactions or a mix of both. I also want PhD/MCS students interested in better understanding the issues of current VR/AR HMDs regarding perception by quantifying their effect on user performance and learning.

Accepting: PhD and MCS students

 in working with Dr. Mayra Barrera Machuca.

Existing cognitive models of planning (e.g., in games like chess) tend to pre-specify possible planning models as anchored to classic algorithms, such as MDP solvers and stochastic search. In contrast, people likely maintain and learn an evolving library of planning strategies encoded as mental programs, and grow this library through experience. In this project, we explore approaches to modeling how such libraries of programs evolve and grow through social interaction and experience. We will work in collaboration with cognitive and developmental psychologists to build AI that can grow and learn like a child.

Accepting: PhD and MCS students

 in working with Dr. Nils Wilde

Socially Sustainable Software Development means creating and maintaining software systems that promote social equity, well-being, and inclusivity by ensuring fair access to resources and opportunities, supporting diverse user needs, and fostering community engagement and participation. The successful applicant will develop and empirically evaluate tools or practices for improving software sustainability. The ideal candidate has professional experience in software development and a keen interest in ethics.

Accepting: PhD and MCS students

 in working with Dr. Paul Ralph.

Evidence standards are models of a scientific community鈥檚 expectations for research: how research should be conducted: what should be reported in scientific articles; how much and what kind of evidence is needed to justify claims about the world. The successful applicants will join the ACM SIGSOFT Evidence Standards project, improve existing evidence standards, and use them to develop tools to support research, scientific writing, and peer review. The ideal candidate has good knowledge of web programming (e.g. HTML, CSS, Javascript) and a keen interest in science and research.

Accepting: PhD and MCS students

 in working with Dr. Paul Ralph.

In this research project, we are going to work on monitoring and analysis of adversity and changes in the communication networks and services using machine learning and artificial intelligence approaches. I'm looking for interested students who are capable of independent as well as team based research on both wired and wireless networks, including the internet of things and vehicular networks.

Accepting: PhD and MCS students

 in working with Dr. Nur Zincir-Heywood.

Large Language Models, such as ChatGPT, Google Bard, Copilot, and other artificial intelligence (AI) systems, possess the capability to generate code based on natural language descriptions. Previous research on AI code generators has primarily focused on assessing their usability for novice programmers and highlighting their advantages for curriculum development in educational settings. Although these studies have yielded valuable insights, there remains considerable gaps in learning sciences research with respect to the potential benefits for novice programmers who face challenges and the inherent limitations with relying extensively on code generated by these tools. Based on information processing theories related to skill acquisition and program comprehension in introductory programming, this research aims to gain insights into learning, transfer, and performance of students using AI code generators. 

Accepting: PhD students

 in working with Dr. Eric Poitras.