网红黑料

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.

Autonomous robots increase efficiency by supporting human workers in environments such as hospitals, office spaces, industrial facilities, or personal homes. Furthermore, drones, autonomous ground vehicles and vessels provide flexible tools for outdoor informat