log anomaly detection toolkit including DeepLog

Pytorch Implementation of DeepLog.

FloydHub porting of Pytorch time-sequence-prediction example

Four digit SVHN (Street View House Number) sequence prediction with CNN using Keras with TensorFlow backend

Temporal Convolutional Network for Sequence Modelling

Predict next number in a sequence using a simple ANN. Modularized code with classes for data preparation, neural network architecture, and training.

biLSTM model with the attention mechanism. Example of prediction/inferencing included.

An Implementation of the Context Tree Weighting (CTW) Sequence Prediction Algorithm

Simple implementation of Hidden Markov Model for discrete outcomes/observations in Python. It contains implementation of 1. Forward algorithm 2. Viterbi Algorithm and 3. Forward/Backward i.e. Baum-Welch Algorithm.

日志异常检测，Used for log anomaly detection, including log processing, training, prediction, and output results.

Baseball pitch sequence prediction using 7 ML models (LSTM, Transformer, CNN, HMM, Random Forest, Logistic Regression, AutoGluon) with synthetic data generation, k-fold benchmarking, ablation studies, and MLflow tracking.

Rock Paper Scissors using Discrete Markov Chains : The program calculates the probability of the opponent picking one of the three states (R/ P/ S) from choices made by the opponent during the previous games.

Project using Compact Prediction Tree Algorithm. Based on the paper "Compact Prediction Tree : A lossless model for accurate sequence prediction"

Prediction of the binding specificity of transcription factors using support vector regression

Contains code for building a simple lstm model to predict hourly Beijing air quality data.

Neural Networks for learning with structured data types

Predicting likely 1D layer-depth sequences based on formations where lateral wells are typical

TreeMemoryPredictor (TMP): Real-time sequence prediction engine built on Dynamic Suffix Tries. Implements Context Mixing and Entropy Scaling to capture variable-order dependencies without neural networks.