Deep Learning

I have started learning about deep learning from 2016. And from that time the flame of passion for this field has been undying.

• Master Thesis on a novel method for medical imaging resolution enhancement by end-to-end simulation of OCT imaging by Monte Carlo simulation and mapping the relation between the underlying physical structure and OCT imaging data.
• Gaussian RBF, deep pose, sentiment analysis with BERT, speech recognition with attention network, medical image segmentation with SegAN.
• Image enhancement with Tenet, body part segmentation with PGAN, image colorization with residual encoder, image super resolution with ESRGAN application development.
• Various paper implementation in the topics of image and text classification and segmentation, body part segmentation, speech recognition, time series prediction, NLP, etc.
• License plate recognition based on novel networks architecture using CNN and LSTM and CTC loss.
• Body transform network based on Nvidia’s Vid2Vid neural network in Pytorch.