Use faceted filters to find projects by title, author, supervisor, department, programme, subject, case study, year, document type and access mode.
I would like to begin by expressing my deepest gratitude to God for providing me with the strength, clarity, and perseverance needed to complete this research. My heartfelt thanks go to my project supervisor, Dr. Oladiran S. OLABIYI, whose expertise, guidan…
This record links to the original Transformer paper, which introduced a sequence modelling architecture based entirely on self-attention. It is useful for repository testing because it contains formal architecture descriptions, experiments, equations, referenc…
This record links to the Mask R-CNN paper, which extends object detection with instance segmentation masks. It gives the repository a realistic external PDF for image analysis, computer vision search, and metadata preview testing.
This record links to the Faster R-CNN paper, which introduces region proposal networks for efficient object detection. It is suitable for testing robotics, intelligent systems, and engineering repository metadata.
This record links to the DeepLab semantic segmentation paper, which combines deep convolutional networks with atrous convolution and structured prediction. It is useful for testing long technical titles and external PDF document rendering.
This record links to the variational autoencoder paper, which introduces a practical approach to variational inference with neural networks. It supports realistic testing of statistics, generative modelling, and advanced research metadata.
This record links to the XGBoost paper, which describes a scalable tree boosting system used widely in data science. It provides a strong test case for statistics metadata, predictive modelling keywords, and external link previews.
This record links to the word2vec paper, which presents efficient methods for learning distributed word representations. It is useful for testing older but influential NLP documents, keyword matching, and public external PDF access.
This record links to the sequence-to-sequence learning paper, which uses neural networks to map input sequences to output sequences. It provides a realistic external PDF for testing NLP repositories, metadata extraction, and citation generation.
This record links to a foundational neural machine translation paper that introduced an attention-based alignment approach. It is useful for testing humanities-adjacent computational linguistics records and external document workflows.
This record links to the EfficientNet paper, which proposes compound scaling for convolutional neural network depth, width, and resolution. It supports realistic testing of undergraduate AI project metadata and external PDF handling.
This record links to the DINO self-supervised vision transformer paper, which studies emergent properties in learned visual representations. It is useful for testing modern machine learning keywords and external document previews.
This record links to the Vision Transformer paper, which adapts transformer architectures to image classification through patch-based image representation. It is useful for validating computer vision categories and AI search relevance.
This record links to the RAG paper, which combines neural retrieval with sequence generation for knowledge-intensive NLP tasks. It provides a strong external PDF test case for repository search, AI assistant context retrieval, and citation workflows.
This record links to the chain-of-thought prompting paper, which studies how intermediate reasoning steps improve large language model performance. It is useful for testing education technology records and AI-assisted learning metadata.
This record links to the LoRA paper, which introduces low-rank adaptation for efficient fine-tuning of large language models. It is useful for testing AI thesis metadata, modern NLP keywords, and external PDF access.
This record links to the latent diffusion models paper, which combines compression and diffusion modelling for efficient high-resolution image synthesis. It is suitable for validating external document access and contemporary generative AI metadata.
This record links to the denoising diffusion probabilistic models paper, which describes a generative modelling framework based on iterative noise reversal. It supports realistic testing for modern AI documents, long keywords, and PDF preview workflows.
This record links to the YOLO object detection paper, which frames detection as a single regression problem over bounding boxes and class probabilities. It is useful for testing engineering project records and real-time vision metadata.
This record links to the U-Net paper, which proposes an encoder-decoder convolutional network for biomedical image segmentation. It provides a realistic health technology document for repository search, previews, and discipline-specific keyword testing.
This record links to the dropout paper, which explains how randomly omitting feature detectors during training can reduce overfitting. It is suitable for testing undergraduate AI project metadata, concise abstracts, and direct external PDF linking.
This record links to the Adam optimization paper, which presents an adaptive learning-rate method widely used in deep learning. It is a compact but realistic technical PDF for testing keyword relevance, citation generation, and external document access.
This record links to the original GAN paper, which introduced adversarial training between a generator and a discriminator. The document is useful for validating machine learning topics, external PDF handling, citation metadata, and repository discovery featur…
This record links to the GPT-3 paper, which evaluates large autoregressive language models under few-shot, one-shot, and zero-shot settings. It is useful for stress-testing long author metadata, AI research keywords, external document display, and abstract sea…
This record links to the BERT paper, which describes bidirectional transformer pre-training for language understanding tasks. It gives the platform a realistic NLP document for search, indexing, keyword generation, citation display, external preview, and metad…