Moseli Mots'oehli's Portfolio

This page holds my portfolio of evidence, towards Ph.D candidacy in Computer Science. My research focuses on image classification, in particular, active learning in the presence of label noise. My ultimate goal is to improve state of the art methods on current benchmarks in this domain, then go on to implement these methods in products with large scale impact.

Statement of Purpose

Statement of Purpose

Core Competency

MS Degree UH Manoa
Qualifying Exam Results

Evidence of Scholarly Ability

Ph.D. Literature Review
Masters Thesis (University of Pretoria)
Publications to Date
  1. Public Parking Spot Detection and Geo-localization Using Transfer Learning : Published in the Proceedings of the 3rd Southern African Conference for Artificial Intelligence Research (SACAIR 2022), pages 109-124, ISBN: 978-0-6397-1978-8, acceptance rate : 60.2%
  2. GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noise : Submitted to Conference name in the US, average acceptance rate : NA
  3. Comparision of Adversarial and Non-adversarial LSTM Music Generative Models : Published in Science and Information (SAI) Conference 2023(Springer), pages 428–458., average acceptance rate : 35%
  4. FishNet: Deep Neural Networks for Low-cost Fish Stock Estimation : To be Submitted to the IEEE International Conference on Image Processing (ICIP 2023)., average acceptance rate : NA
  5. PuoBERTa: Training and evaluation of a curated language model for Setswana : Accepted for presentation at Southern African Conference for Artificial Intelligence Research (SACAIR 2023)., average acceptance rate : NA

Other Evidence of Professional Capacity

  1. 2023: Technical reviewer for Science and Information (SAI) Conference 2024.
  2. 2023: Technical reviewer for Future Technologies Conference (FTC) 2023.
  3. 2023: Technical reviewer for Intelligent Systems Conference (IntelliSys) 2023.
  4. 2022: Technical reviewer for Science and Information (SAI) Conference 2023.
  5. 2022: GSO representative in the ICS department at UH Manoa.
  6. 2018: NeurIPS black in AI poster presentation (Montreal).
  7. 2018: Invited talk: introduction to machine learning (National university of Lesotho).