mini-batch

A simple PyTorch-based neural network that classifies student exam outcomes (Pass/Fail) using study hours and previous exam scores. Implements dataset splitting (train/val/test), mini-batch training, and evaluation with configurable hyperparameters.

Provides a basic edge simulator

Use of various deep learning models to classify flowers. Models are implemented from scratch in PyTorch using only tensor operations.

Predict airplane's status by implementing Linear Regression with Regularization, Batch/ Mini-Batch/ Stochastic Gradient Descent.

Examples of Linear Regression and three Gradient Descent methods (Batch, Stochastic and Mini-Batch)

Early stopping for K-means: stop when only boundary points still switch clusters, and settle them from their own label history. Shorter runs, uncertainty flags, soft memberships. Exact Lloyd, mini-batch and EMA (constant-step) training. scikit-learn compatible.

Graph Attention-based Instance Selection (GAIS). Python package for a novel instance selection method utilizing graph attention networks.

This is an implementation of different optimization algorithms such as: - Gradient Descent (stochastic - mini-batch - batch) - Momentum - NAG - Adagrad - RMS-prop - BFGS - Adam Also, most of them are implemented in vectorized form for multi-variate problems

Usefull python implementation of batch iterator.

Demonstration of generating mini-batches in Tensorlfow from GPU memory.

Tensorflow implementation of asyncronous 1-step Q learning in "Asynchronous Methods for Deep Reinforcement Learning" with improvement on weight update process (use minibatch) to speed up training.

End-to-end Bitcoin analytics and ML pipeline on AWS. Ingests BTC/USD OHLCV (1m) to S3, converts to partitioned Parquet for Athena, validates data, trains a Random Forest volatility model with SageMaker, and serves predictions via a managed endpoint. Dashboards in QuickSight.

Mini-batch SVM / Logistic Regresion, Online learning for large scale data.

A repo holding the implementation as well as some theoretical explanation of the important relevant concepts. It is going to be in development for a long long time. I'll keep adding things everytime I have something to add to it, and I have the time for it. One can use it to learn the basics of Machine Learning from kind of scratch.

TensorFlow Input Pipeline Examples based on multi-thread and FIFOQueue