Md Mesbahur Rahman

Md Mesbahur Rahman

Computer Vision Engineer at DeepX, Inc; MSCS student at UT Austin

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Page Not Found

Abstract:

Page not found. Your pixels are in another canvas.

Citation:

Citation:

Citation:

Citation:

Citation:

Citation:

Citation:

Citation:

Citation:

Citation:

Citation:

Citation:

Citation:

Citation:

Citation:

Posts

Future Blog Post

less than 1 minute read

Abstract:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Citation:

Blog Post number 4

less than 1 minute read

Abstract:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Citation:

Blog Post number 3

less than 1 minute read

Abstract:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Citation:

Blog Post number 2

less than 1 minute read

Abstract:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Citation:

Blog Post number 1

less than 1 minute read

Abstract:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Citation:

portfolio

projects

Facial Keypoint Detection using CNN Haar Cascade Classifier

Abstract:

Facial keypoint detection is an important example of a computer vision problem which can be solved effectively by treating the problem as an image regression task and and trainign a CNN network for predicting the image location of the key-points. In this project, I trained a CNN network to predict important facial keypoints given an image of a human face. I did this project as a requirements of graduating from Udacity's Computer Vision Nanodegree program.

Citation:

Image Caption Generation using CNN LSTM Encoder Decoder

Abstract:

Image caption generation is a widely used application of sequential generative model. In this project, I designed and trained a CNN-LSTM encoder-decoder architecture for generating caption from an input image. I did this project as part of the requirement of gaduating 'Computer Vision Nanodegree' from Udacity.

Citation:

Unsupervised Anomaly Detection Using Convolutional Autoencoder

Abstract:

Anomaly detection is a very common and important problem to solve in industrial setting. There are several aproach exists for doing Anomaly Detection using Deep Learning. One of the most effective (both in terms of performace and model training cost) is to utilie unsupervized anomaly detection using Convolutional Autoencoder. In this project, I designed and trained an Convolutional Autoencoder model for detecting anomaly image (images of digit 3 in MNIST dataset) by considfering images of digit 1 as regular image.

Citation:

Autonomous agents for realtime multiplayer ice-hockey

Abstract:

We designed an agent to play SuperTuxKart, and particularly compete with the AI oracle (and other classmate AI agents) in a 2v2 hockey game. Our strategy was to maximize puck possession and minimize puck distance to the opponent’s goal. Imitation Learning and DAgger could not perform sufficiently well when trained using the AI oracle of the game. Instead, an internal state controller was built and found superior to the AI, where it wins 70% of the time and scores an average of 3.1 goals per game when competing in 2v2 against the AI oracle. Based on supervised learning, a planner was trained to detect puck presence and location. Playing 10 2v2 games, this agent wins 30% of the games and scores an average of 1.2 goals per game. Future work can involve training a DAgger learner on the internal state controller.

Citation:

Analyzing and Mitigating Dataset Artifacts

Abstract:

In NLP research arena Benchmark datasets are often used to compare the performance of different SOTA models. But a high held-out accuracy measure neither conveys the whole story about a model's strengths and weaknesses nor it can guarantee that the model has meaningfully solved the dataset. The model can just learn some spurious correlation in the dataset and can still achieve some high accuracy. This phenomenon is known as Dataset Artifacts and in this project, we tried to identify some cases of it for the ELECTRA-small (Clark et al., 2020) model on the SQuAD problem setting using Checklist and Adverserial Dataset frameworks and took attempt of mitigating some of the Dataset Artifacts using Dataset Inoculation by fine-tuning strategy.

Citation:

Designing and Training a Fully Attentive Multimodal Transformer Network for Medical Visual Question Answering Task

Abstract:

Medical Question Answering is a very important and impactful application of Multi-modal learning. It can contribute to the interpretability of machine learning model in medical applications, reduce workload of medical professional, and can be a part of fully automated healthcare system. In this project, we have done a background research on the state of the art of Medical Visual Question Answering research. Based on some latest well performing paper, we propose our own fully attention based Transformer only network for solving the medical visual question answering task by treating a multi-class classification problem. We also present some analysis on hyperparameter tuning of the model, compare its performance with models from some other notable papers and suggest some future improvements of our model.

Citation:

publications

talks

teaching

Lecturer at Uttara University

Undergraduate course, Uttara University, Department of Electrical and Electronics Engineering, 1900

Abstract:

  • Taught undergraduate level course in the department of Electrical Engineering at Uttara University, Dhaka, Bangladesh
  • List of course taught as a lecturer: ELECTRONICS-I (EEE 201), ENERGY CONVERSION-I (EEE 205), ELECTRICAL PROPERTIES OF MATERIALS (EEE 351) MICROPROCESSOR AND INTERFACING LAB (EEE 312)

Citation: