Madjeisah

adinkra-symbols-classification

augmentation-with-Augmentor-

augmentation-with-imgaug

Books-for-Data-Scientist

Chinese-Twi_translation

NMT experiments on Chinese-Twi parallel Bible corpus with the state-of-the-art Transformer model, a self-attention encoder-decoder model.

feature-transformer

Treating a network as an arbitrary feature extractor

fxREG

fxREG: Frobenious norm Graph Laplacian Regularization for Node and Graph Classification

GCP

A novel graph contrastive multiview learning via pre-training framework (GCP).

gda-overview

Towards Data Augmentation in Graph Neural Network: An Overview and Evaluation

Get-Things-Done-with-Prompt-Engineering-and-LangChain

Madjeisah/gda-overview

Towards Data Augmentation in Graph Neural Network: An Overview and Evaluation

Madjeisah/Chinese-Twi_translation

NMT experiments on Chinese-Twi parallel Bible corpus with the state-of-the-art Transformer model, a self-attention encoder-decoder model.

Madjeisah/SCMvL

A Search-based Contrastive Multi-View Learning for Graph Classification

Madjeisah/adinkra-symbols-classification

Madjeisah/augmentation-with-Augmentor-

Madjeisah/augmentation-with-imgaug

Madjeisah/Books-for-Data-Scientist

Madjeisah/feature-transformer

Treating a network as an arbitrary feature extractor

Madjeisah/fxREG

fxREG: Frobenious norm Graph Laplacian Regularization for Node and Graph Classification

Madjeisah/GCP

A novel graph contrastive multiview learning via pre-training framework (GCP).

Madjeisah/Get-Things-Done-with-Prompt-Engineering-and-LangChain

Madjeisah/Madjeisah

Config files for my GitHub profile.

Madjeisah/Madjeisah.github.io

Madjeisah/markdown-cheatsheet

Markdown Cheatsheet for Github Readme.md

Madjeisah/Network-Information-Security

Network Information Security Course

Madjeisah/NLP-Interview-Task

NLP Interview Task - University of Birmingham Medical School

Madjeisah/respred

A Novel Respiration Pattern Biometric Prediction System Based on Artificial Neural Network

Madjeisah/tw-parallel-corpus

We detailed the modelling of a massively parallel bible corpus based on Twi, a common Ghanaian language to a handful of languages. We talk through some of the common issues we encountered in obtaining, processing, converting and formatting of the corpus as well as the latent desire for success in natural language processing. The sentence aligned data is stored in various files based on the Twi to the selected language pairs with comma delimited tab separation, so that verses with the same line number in a line pair are mappings of each other. Finally, we present a statistical analysis of the corpora collected based on selected text categorization models for text classification by leveraging vector embedding (like Word2Vec). Results are presented in Extra Trees-based word-embedding models and text classification models like Naive Bayes (NB), and linear kernel Support Vector Machine (SVM). We also engaged a version that uses frequency-inverse document frequency (TF-IDF) weighting scheme, which reveal interesting clues into the challenges ahead.

Madjeisah/tw-parallel-lg-corpus

Chinese-Twi Corpus is the first attempt on Chinese-Twi corpora with about 31,103 parallel-aligned sentences.