My
Projects
As a dedicated AI/Machine Learning Engineer with a proven track record of delivering impactful solutions, I have developed sophisticated models that address real-world challenges. My projects emphasize advanced techniques in AI/ML, ranging from image quality enhancement using deep learning to multi-class text classification with pre-trained transformer models. Each initiative reflects my commitment to driving innovation and measurable outcomes in the AI domain.
-
Developed a Multi-Class Text classification model to categorize the text category into five classes (name, gender, dob, address and other) with imbalanced distribution.
-
Utilized BERTTokenizer and BertForSequenceClassification to preprocess and fine-tune a pre-trained BERT model for domain-specific tasks, achieving an F1 Score of 80% on the validation set.
-
Leveraged various algorithms to enhance the quality of the image specifically our dataset includes the license plates.
-
Implemented trained model with the autoencoder, UNet, and GAN, as well as used evaluation metrics PSNR, SSIM, per-pixel loss, and perceptual loss.
This project is mainly created for my AI/ML fellows, this covers all AI/ML algorithms and libraries fundamentals with their code and explanation along side
