Python implementation of an N-gram language model with Laplace smoothing and sentence generation.

Ngrams with Basic Smoothings

Built a system from scratch in Python which can detect spelling and grammatical errors in a word and sentence respectively using N-gram based Smoothed-Language Model, Levenshtein Distance, Hidden Markov Model and Naive Bayes Classifier.

Offical implementation of "Adaptive Smoothing Gradient Learning for Spiking Neural Networks", ICML 2023

Revisiting Whittaker-Henderson Smoothing

Ngrams with Basic Smoothings

A Bigram Language Model from scratch with no-smoothing and add-one smoothing. Outputs bigram counts, bigram probabilities and probability of test sentence.

Ngrams with Basic Smoothings

Ngrams with Basic Smoothings

PRESS: Predictive State Smoothing in Python (tf.keras)

In this section, we will perform time series analysis by participating in the Gdz Elektrik Datathon 2023 competition.

An NLP project leveraging character trigrams and smoothing techniques (Lidstone, Linear Discounting, Absolute Discounting) for language identification. Trained on for Spanish, Italian, English, French, Dutch, and German, achieving 99.8932% accuracy. Includes datasets, model parameters, and comprehensive documentation.

Implementation of smoothing-based optimization algorithms

Ngrams with Basic Smoothings

Ngrams with basic smoothing.

SUPERVISED LEARNING: REGRESSION: Linear - Polynomial - Ridge/Lasso CLASSIFICATION: K-NN - Naïve Bayes - Decision Tree - Logistic Regression - Confusion Matrix - SVM TIME SERIES ANALYSIS: Linear & Logistic Regr. - Autoregressive Model - ARIMA - Naïve - Smoothing Technique UNSUPERVISED LEARNING: CLUSTERING: K-Means - Agglomerative - Mean-Shift - F…

A secure Image Processing pipeline based on Homomorphic Encryption, capable of performing various central tasks. Most notably, it includes matching encrypted images using the SIFT algorithm.

Methods for numerical differentiation of noisy data in python