Over the next ten years, computer science graduates are poised for extraordinary opportunities, particularly as the baby-boomer generation begins their retirement phase. Acadia University, which consistently ranks in the top three for undergraduate studies in Canada, offers superior degree programs in computer science. Our students receive a comprehensive education in computer science and their interpersonal and team skills are honed through project-oriented courses and cooperative education options.

We invite you to explore our website, investigate the various degrees and certificate programs, our areas of research, funding opportunities, and also our cooperative education program. Most importantly, get to know our faculty and students through the many resources on the website. From this we think you'll discover why our motto is "Come as a student, leave as a colleague".

 

 

MSc Computer Science defense

Student: Excellence Sowunmi

Title: Bridging External Symbols with Internal Subsymbolic Learning and Reasoning Using Cross-Modality Autoencoders.

Date and time: Friday, April 11th, 9:30am

Location: On Teams

Join the meeting now

Meeting ID: 216 795 347 159

Passcode: p3A6bg9Q

 

Abstract:

 Neuro-symbolic AI seeks to integrate the strengths of subsymbolic learning and symbolic reasoning. A key challenge in this integration lies in developing a unified internal

representation that supports both perceptual understanding and abstract inference across modalities. While neural networks are effective at processing sensory data

such as images and text, they often lack symbolic interpretability. Conversely, symbolic systems are limited in their ability to handle complex, high-dimensional inputs.

This thesis addresses this gap by introducing a cross-modal autoencoder architecture that learns subsymbolic bidirectional transformations between images and text.

These learned representations are then used to interpret external symbols (text) or generate them as explanations for concepts (images).

 

Grounded in the neuro-symbolic framework proposed by Silver and Mitchell, the model distinguishes between conceptual representations (conrep), which capture internal subsymbolic features from perceptual inputs, and symbolic representations (symrep), which enable external symbolic communication. The architecture encodes an image into a conrep and transforms it into a symrep for symbolic decoding, and conversely can map textual input into a symrep before decoding it as a conrep for image reconstruction. This bidirectional mapping supports both learning and reasoning across modalities.

 

To support robust multimodal reasoning, the system employs a shared reasoning layer, selective input masking, and a curriculum-based training strategy. The model is first trained on unimodal tasks before progressing to cross-modal generation, stabilizing learning and promoting better symrep–conrep alignment. Empirical evaluations—including standard testing, cross-validation, and qualitative inspection— demonstrate that the model performs stable and accurate reconstructions, even when one modality is masked.

 

This work contributes a unified neuro-symbolic learning framework that integrates symbolic and conceptual representations through structured training and shared latent reasoning. The proposed approach enables interpretable and resilient cross-modal inference, with applications in computer vision, natural language processing, and multimodal reasoning tasks.

 

Committee:

Drs. Danny Silver & Andrew McIntyre, Supervisors

Dr. Frank Rudzicz, Dalhousie Univ., External Examiner

Dr. Sazia Mahfuz, Internal Examiner

Dr. Darcy Benoit, Director of the School of Computer Science

Dr. Holger Teismann, Chair of the defence