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.

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.

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

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.

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

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

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

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

Neural Networks for learning with structured data types

The repository includes implementations of quaternion networks and new QALE loss function, which calculates the error value based on the difference in angles between the result and the expected value. Procedures for performing the training and evaluation of predicting successive elements of a rotation sequence are also provided.