Machine Learning Engineer

Profile
Contacts

Summary

My focus is applying machine learning algorithms into a real-world application. I have expertise of 2.5+ years on this area. Some of my previous works include image classification with different backbones like Resnet, VGG, Mobile Net, Squeeze Net, object detection with complex algorithms like Faster RCNN and YOLO, image segmentation using U-Net. I am currently working my research on image captioning that brings both computer vision and natural language together. I use Faster RCNN as region proposal network and transformer (self-attention) for caption generation. Prior to this I was using LSTM as the caption generator. Here are some projects I have done so far:
- Hand gesture detection using Convolutional Neural Network
- Epilepsy detection using convolutional neural network from ECG data and etc
- Scene graph generation - LSTM, Faster RCNN.
- Pick and Place Robot: After object is detected using YOLO algorithm, robot arm will pick and place
- Number detection from natural scene
In summary I am familiar with algorithms like CNN, LSTM, Transformer, Yolo, Faster RCNN, Vision Transformer, Resnet, Mobile Net, attention mechanisms and so on. I mostly use Pytorch for training the models. You can reach me out on my email any time.

Expectations

I am looking for a job where I can invest my knowledge of deep learning. I look for a strong team in which I work together, share experience and achive something great. I want to contribute further in developement of this technology.