PhD Research Proposal
DR01 - To Improve Reasoning of LLMs
DR02 - To Advance HMI
Deep Learning
DL00 - The whole idea behind Convolutional Neural Networks (CNNs)
DL01 - Activation, Optimization, and Loss Function
DL02 - Deeper CNN Variants and their Architecture
DL03 - Recurrent Neural Networks(RNNs) and difficulty in training
DL04 - LSTM and GRU
DL05 - Encoder-Decoder, Attention Mechanism and Transformers
DL06 - Generative Adversarial Networks(GANs) and its variants
DL07 - AutoEncoder and its variants
Self Supervised Learning
SSL01 - Self-Supervised Learning - CPC, Deep InfoMax, SimCLR
SSL02 - Self-Supervised Learning - MoCo, BYOL, SwAV, SimSiam
Federated Learning
FL01 - Federated Learning (FedAvg)
Computer Vision
CV00 - Basics of Image Processing
CV01 - Image Transformation
CV02 - Feature Detection and Matching
CV03 - Object Detection Models - Two-stage Detectors (SS, RCNN based)
CV04 - Object Detection Models - One-stage Dectectors (YOLO, RetinaNet)
CV05 - Evaluation Metrics used in CV problems
CV06 - Image Segmentation - UNet, MaskRCNN
Reinforcement Learning
RL00 - Markov Decision Process (MDP)
RL01 - Policies and Value Function
RL02 - Monte Carlo Methods and Control
RL03 - Off-Policy via Importance Sampling
RL04 - TD Learning
RL05 - SARSA and Q-Learning
RL06 - n-step Bootstrapping
RL07 - Deep Q-Learning and Double Q-Learning
RL08 - Policy Gradient Methods & REINFORCE
Statistics Essentials
ML01 - Basic Statistics
ML02 - Probability Distributions
ML03 - Statistical Tests

Konark Karna | AI Blog

AI NOTEBOOK
RESUME
BOOKSHELF

Image Segmentation - UNet, MaskRCNN

deep-learning
computer-vision

Dec 24, 2023

This work is licensed under a Attribution-NonCommercial 4.0 International license.

PREVIOUSCV05 - Evaluation Metrics used in CV problems

NEXTRL00 - Markov Decision Process (MDP)

© Konark Karna | AI Blog 2021, Powered by Jekyll & TeXt Theme.

Search