Moduleformer: Learning modular large language models from uncurated data

Y Shen, Z Zhang, T Cao, S Tan, Z Chen… - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models (LLMs) have achieved remarkable results. But existing models are
expensive to train and deploy, and it is also difficult to expand their knowledge beyond pre …

An incremental learning approach to automatically recognize pulmonary diseases from the multi-vendor chest radiographs

M Sirshar, T Hassan, MU Akram, SA Khan - Computers in Biology and …, 2021 - Elsevier
The human respiratory network is a vital system that provides oxygen supply and
nourishment to the whole body. Pulmonary diseases can cause severe respiratory …

A novel incremental learning driven instance segmentation framework to recognize highly cluttered instances of the contraband items

T Hassan, S Akcay, M Bennamoun… - … on Systems, Man …, 2021 - ieeexplore.ieee.org
Screening cluttered and occluded contraband items from baggage X-ray scans is a
cumbersome task even for the expert security staff. This article presents a novel strategy that …

Knowledge distillation driven instance segmentation for grading prostate cancer

T Hassan, M Shafay, B Hassan, MU Akram… - Computers in Biology …, 2022 - Elsevier
Prostate cancer (PCa) is one of the deadliest cancers in men, and identifying cancerous
tissue patterns at an early stage can assist clinicians in timely treating the PCa spread. Many …

Rehearsal-Free Modular and Compositional Continual Learning for Language Models

M Wang, H Adel, L Lange, J Strötgen… - arXiv preprint arXiv …, 2024 - arxiv.org
Continual learning aims at incrementally acquiring new knowledge while not forgetting
existing knowledge. To overcome catastrophic forgetting, methods are either rehearsal …

Jointly exploring client drift and catastrophic forgetting in dynamic learning

N Babendererde, M Fuchs, C Gonzalez… - arXiv preprint arXiv …, 2023 - arxiv.org
Federated and Continual Learning have emerged as potential paradigms for the robust and
privacy-aware use of Deep Learning in dynamic environments. However, Client Drift and …

[PDF][PDF] State-of-the-Art Techniques in Artificial Intelligence for Continual Learning: A Review.

B Salami, K Haataja, PJ Toivanen - FedCSIS (Position Papers), 2021 - annals-csis.org
Artificial neural networks are used in many state-of-the-art systems for perception, and they
thrive at solving classification problems, but they lack the ability to transfer that learning to a …

[HTML][HTML] Automatic labeling to overcome the limitations of deep learning in applications with insufficient training data: A case study on fruit detection in pear orchards

M Culman, S Delalieux, B Beusen, B Somers - Computers and Electronics …, 2023 - Elsevier
Accurate counting of pears in orchard environments is essential for crop management.
However, due to the time and labor cost of manual counting, farmers rely on sampling a few …

U-TELL: Unsupervised Task Expert Lifelong Learning

I Solomon, APP Aung, U Kumar, S Jayavelu - arXiv preprint arXiv …, 2024 - arxiv.org
Continual learning (CL) models are designed to learn new tasks arriving sequentially
without re-training the network. However, real-world ML applications have very limited label …

Negotiated Representations for Machine Mearning Application

N Korhan, S Bayram - arXiv preprint arXiv:2311.11410, 2023 - arxiv.org
Overfitting is a phenomenon that occurs when a machine learning model is trained for too
long and focused too much on the exact fitness of the training samples to the provided …