Artificial Intelligence Innovation Laboratory

UB's Artificial Intelligence Institute brings together educators and researchers to advance machine or human-machine systems that can address complex cognitive tasks.

UB Researchers Host Finnish Delegation

9/20/21

Researches from SEAS recently hosted a delegation from Finland after signing a research and funding MOU with Allied ICT Finland (AIF)

previous next

Interdisciplinary Research

Playing a key role in bringing together researchers in SEAs, across campus and from around the world.

Local NY Partnerships

We work closely with many western NY companies to provide interns and research expertise

Undergraduate Research

UB undergrads have the opportunity to work with MS and PhD Research Teams on exciting projects

Our Laboratory

About Us

The Artificial Intelligence Innovation Lab (A2IL) is focused on advancing the field of AI and its applications. While our core competencies are related to computer vision, language processing, machine learning and human computer partnerships, our goal is to bring together multidisciplinary research teams to address AI related problems in a variety of domains.

Learn More About A2IL>

Our Research

previous next

Action Prediction
10/18/22
Anticipating human actions addresses the problem of predicting what a person is going to do next and how they will perform it. In this project, we try to jointly predict human action categories and skeleton pose joints.
Chart Analysis
10/18/22
Detection, Recognition, Analysis and Extraction of Chart Content.
Document and Figure Linking
10/18/22
Intra-and Inter-Document association of referring text with referenced content.
FMonet
10/18/22
Face Morphing with adversarial NETworks.
HVAC Diagnosis and Predictive Analysis
10/18/22
Heating, ventilation and air conditioning (HVAC) systems account for up to 50% of energy costs of a typical building in the United States. These complex systems require expert knowledge to maintain, and optimizing their performance can depend on factors that are unrelated to the systems themselves.
LEARM
10/18/22
Latent Expression Analysis and Recording Model: Aimed at human behavior modification research, this project involves developing an interface that brings together the recording of human reactions to different stimuli and apply existing deep learning capabilities to analyze those reactions in three different areas - video (facial reactions), audio (voice) and text (answers to the stimuli).
Medical Image Analysis
10/18/22
Nuclei segmentation in histology images is an import step for identifying cells and doing analysis for problems such as disease identification and/or progression. In this effort, we focus on the lack of sufficient labeled nuclei segmentation data and synthesize diverse data through adversarial network for the nuclei segmentation task.