I am a masters student at TUM, focusing on Machine Learning, Robotics and Formal Methods. I have experience as a software engineer from my time with Samsung Research, Bangladesh. My research interests lie in designing intelligent deep models and applying them in various paradigms. I have a keen interest in using deep learning to improve reinforcement learning systems.
Master of Science in Informatics, 2022
Technical University of Munich
B.Sc. Engineering in Computer Science and Engineering, 2017
Islamic University of Technology
Development frameworks
Languages
Shell
In this post, we will be looking at the paper PnPNet: End-to-End Perception and Prediction with Tracking in the Loop, by Liang et al., which was published in CVPR 2020 [1]. After defining our task and discussing some related research in this field, we will be looking at the methodology of the paper. Then we will analyze the quantitative results and have a look at the qualitative results. Finally, we will finish it off with some remarks and possible ideas for extension.
Implementation of Advantage Actor Critic to solve OpenAI LunarLander environment
Implementation of Deep Q Learning to solve OpenAI LunarLander environment
Implementation of Double Deep Q Learning to solve OpenAI LunarLander environment
Implementation of Dueling Deep Q Learning to solve OpenAI LunarLander environment
Implementation of Dueling Double Deep Q Learning to solve OpenAI LunarLander environment
Implementation of REINFORCE to solve OpenAI LunarLander environment
Implementation of SAC to solve OpenAI LunarLander environment
Implementation of Value Actor Critic to solve OpenAI LunarLander environment
Approaches and code for identifying cacti from satellite images
Description of approaches for the APTOS medical image classification Competition
Classifying fruits using computer vision models
Vision model to classify facial expression
Approaches and codes for short-text binary classification
Recursion Cellular Image Classification
SIIM-ACR Pneumothorax Segmentation
Performance analysis of Tabular vs Vision models on Digits-MNIST dataset