RNN architectures trained with Backpropagation and Reservoir Computing (RC) methods for forecasting high-dimensional chaotic dynamical systems.

A data-driven method to calculate the Lyapunov exponent of a dynamical system employing a GRU-RNN.

Deep Learning notes and practical implementation with Tensorflow and keras. Text Analytics and practical application implementation with NLTK, Spacy and Gensim.

Weather forecasting using recurrent neural network

The final project for ECE C147/C247, which evaluates the performance of CNN + Transformer and CNN + GRU + SimpleRNN models on an EEG dataset.

Multiclass Multilabel prediction for stack overflow Questions using NLP

Trigger word detection is the technology that allows devices like Amazon Alexa, Google Home, Apple Siri, and Baidu DuerOS to wake up upon hearing a certain word

Code and data for the NLLP 2021 paper: `Multi-granular Legal topic Classification on Greek Legislation`

🤖 🔠 Making the vaccine sentiment classifier using tweets as datasets with the help of Pytorch Neural Networks and Glove word embeddings. Using both feed-forward nets and bidirectional stacked RNNs.

Siamese Manhattan Bi-GRU for semantic similarity between sentences

An attempt to collect and use data to find a player's "Patterns of Play". These can be exploited in a match.

Collection of my Deep Learning and Machine Learning notebooks.

Used RNN architectures to classify the respiratory sound samples into four different categories. This will in turn help detect respiratory diseases in patients.

A simple Twitter bot which tries to mimic Donald Trump

My repo of assignments for the AUEB M.Sc. in Data Science (2018-2020)

Gated Recurrent Units (GRUs) are a type of RNN designed to capture long-term dependencies in sequential data

Recurrent neural network with GRUs for trigger word detection from an audio clip

Seq2Seq model that restores punctuation on English input text.