**Blog Index**

Recently I received thoughtful feedback from *N Rukkumani** *to create a catalogue for the blogs written so far. So I’ve decided to do the same for easy access depending upon the readers’ topic of interest.

**Machine Learning**

*Introduction to Machine Learning, Deep Learning and Data types*

**Outlier Detection**

*Outliers — Exploratory Data Analysis*

*Feature(Data) Engineering — A gentle introduction to Outliers*

*Anomaly Detection Histogram-based Outlier Score(Pyod/Pycaret)*

*DBSCAN(Density-Based Spatial Clustering of Applications with Noise) for Outliers*

*LOF (Identifying Density-Based Local Outliers)*

*Connectivity-based Outlier Factor(COF)*

*Anomaly detection — Implementation of DBSCAN, LOF & COF in python*

*Handling of Outliers using Gaussian Distribution(probability density function)*

*Subspace Outlier Detection(SOD)*

*KNN, AvgKNN & MedKNN for identifying outliers*

*Stochastic Outlier Selection(An Affinity based Technique) — Part I*

**Machine Learning — Supervised Learning**

*Linear Regression — A Supervised Learning Algorithm*

*Implementation of Linear Regression using Python package*

*Linear Regression Model Improvisation*

*Logistic Regression — A supervised Learning (Classification) Algorithm*

*Implementation Of Logistic Regression — Sklearn package*

*Implementation of Logistic Regression from scratch in python*

*Supervised Learning Algorithm — K Nearest Neighbour(Lazy Learner)*

*Implementation of K Nearest Neighbour using sklearn*

*Naive Bayes Algorithm(Supervised Learning)*

*Implementation of Naive Bayes’ Algorithm*

*Naive Bayes as a Regressor (Quantitative outcome)*

*Support Vector Machine(Supervised Learning)*

*Implementation of Support Vector Machine for classification*

*Decision Tree(A Supervised Learning algorithm)*

*Decision Tree (Handling of continuous data & Regression)*

*Implementation of the Decision tree(sklearn), Pruning & Truncation*

*Random Forest(Ensembling + Bagging)*

*Implementation of Bagging Classifier & RandomForestClassifier*

*Boosting Classifier(an ensemble technique)*

**Recommender Systems**

**Deep Learning**

*Implementation of a binary Classifier using Simple Neural Networks*

*Weights initialization and Minibatches in NN*

*Batch Normalisation, Drop out & Early Stopping*

*Implementation of optimization techniques — part1*

*Implementation of optimization techniques — part2*

*Convex Vs Non-Convex & Saddle points in NN*

*Implementation of SGD, RMSProp & Adam*

*Model Checkpoint, LR reduction & Callbacks(History)*

*Implementation of an Image Classifier using FullyConnectedNeuralNets*

**Convolution Neural Networks(CNN)**

*Convolutional Neural Nets for Images*

*Implementation of an Image Classifier using ConvNets*

*Transfer Learning & ImageNet Datasets*

*Implementation of Pretrained Models for Image Classifier*

*Introduction to Object Localisation & Object Detection*

*Object detection (Fast R-CNN Vs Faster R-CNN)*

*All about IOU (Interpretation, Visualization, and Evaluation)*

*YOLO(You Only Look Once) for object detection*

*YOLOV2 / YOLO9000 (Better, Faster & Stronger) — part1*

*YOLOV2 / YOLO9000 (Better, Faster & Stronger) — part2*

*YOLOv3: An Incremental Improvement*

*Custom Object detector setup(yolov5)*

*YOLOv4: Optimal Speed and Accuracy of Object Detection — Part 1*

*YOLOv4: Optimal Speed and Accuracy of Object Detection — Part 2*

*YOLOv4: Optimal Speed and Accuracy of Object Detection — Part 3*

*Variants of IoU {GIoU, DIoU, CIoU}*

The Swish and Mish activations

*YOLOv4 setup for Custom object detection*

*Kalman Filter(one of the fundamentals of object tracking)*

*Hungarian Algorithm for object tracking*

*Object tracking based on Centroid*

*Simple Online And Real-time Tracking*

*SORT with a Deep Association Metric*

*Implementation of a simple object detector(YOLOv5)*

*Evaluation Metrics for Object detection*

*Implementing an object Tracker for German Shepherd — part1*

*Identification of fps of a video*

*Implementing an object Tracker for German Shepherd — part2*

*EfficientNetV2: Smaller Models and Faster Training*

*Implementation of Autoencoders(Dimensionality Reduction)*

*Siamese Neural Networks for One-shot Image Recognition*

*Vision Transformers (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)*

*MLP Mixer for Vision(latest release by Google)*

*VarifocalNet: An IoU-aware Dense Object Detector*

*Rethinking ImageNet Pre-training*

*Rethink Transfer Learning in Medical Image Classification*

**Satellite Imagery(Remote Sensing)**

*Object Detection in Optical Remote Sensing Images*

*Semantic Segmentation of Satellite Images*

*Satellite Images for Vegetation(Spectral band perspective)*

*Retrieving Satellite Images in different bands & indices*

*Geemap for satellite imagery data exploration*

*Extraction of pixels from Satellite image*

**Natural Language Processing(NLP)**

*A Gentle Introduction to NLP(Natural Language Processing)*

*NLP Data Preprocessing — Part 1*

*NLP Data Preprocessing — Part 2*

*NLP Data Preprocessing — word embeddings(part3)*

*Recurrent Neural Networks(RNN)*

*Forward pass & Backpropagation in RNN*

*Implementation of RNN(Sentiment Analysis)*

*A gentle introduction to LSTM(Long Short Term Memory)*

*Encoder & Decoder basic principle(Language Translation)*

*Evaluation Metrics for NLP(Bleu score)*

*Attention Is All You Need(an intro to Transformers)*

*Transfer Learning in NLP(BERT)*

**Reinforcement Learning**

*A quick glimpse of Reinforcement Learning*

*Markov’s(chain, reward, decision)*

*Policy, Episode & Value function*

*Q function, types of learning & environments*

*Gym ToolKit for RL Simulated Environment*

*Generating an episode using Gym toolkit*

*Continuous State Space Environments*

*Atari Game & other Environments in Gym*

**Cloud Computing**

**Activeloops**