Tokenization is a way of separating a piece of text into smaller units called tokens. Here, tokens can be either words, characters, or subwords. Hence, tokenization can be broadly classified into 3 types – word, character, and subword (n-gram characters) tokenization.

Self-study java neural network library

The repo contains the base code for the experiment conducted by DeepMind and published in Nature under the title 'Advancing mathematics by guiding human intuition using AI'. The data set contains various numeric dat about generic mathematical entities called Knots. A feed-forward neural network was employed to find pattern amongst knot attributes.

A list of awesome AI Model API providers, platforms, projects

Some implementation practice of Keras using Tensorflow backend

Research project titled Semi-supervised learning in NLP models with data augmentation, and iterative noisy students

A self driving car simulation built using Neural Networks

This is a repository which serve for developing deep learning

Named Entity Recognition using Bidirectional LSTM CRF (Bi-LSTM-CRF) network.

The project aims to predict the volume of traffic flow between Minneapolis and St. Paul at a specific point in Minnesota. My task is to build a multi-step RNN with LSTM model that makes a single prediction point of the traffic volume 2 hours into the future, given the previous 6-hour window.

AI + Machine Learning + Deep Learning + Neural Networks = Self-Learning Adventure

Нейросеть для распознавания англоязычных букв

Courses

Simple neural network and automatic differentiation implementation

A Parallelized Number Plate Detection System developed for Windows using Visual Studio. It utilizes OpenCV and OpenMP to efficiently detect number plates in images and recognize characters on them. The primary goal of this system is to speed up the process of detecting and recognizing number plates in images or video frames.

Learn Pytorch framwork by running code line by line

Computational Intelligence first project.

A Matlab implementation of probablistic machine learning models