psycoplankton Goto Github PK

bitpredict--bitcoin-price-forecasting-model

BitPredict is a time series forecasting machine learning project through which I have applied my knowledge of Linear layers, LSTM layers, Convolutional Layers and other concepts into predicting the bitcoin prices using the historical prices dataset from October 2013. All the useful resources are mentioned in the notebook.

dvc_project

A very basic machine learning model which uses dvc for data version control

fuzzy-representation-learning

A Fuzzy Pre-procressing layer which can be used with embeddings to enrich the information content.

gpt-decoded

An implementation of the GPT(generative pretrained transformer) model, from scratch, which produces Shakespearean text by training on the dialogues written by Shakespeare along with the GPT Encoder.

mlops

A MLOPS project which uses zenml, mlflow and streamlit to create pipelines and deploy the model

mnist_with_lightning

A small project using pytorch lightning and hydra packages to classify MNIST and CIFAR10 datasets. Aim is to get familiar with lightning module and hydra-core

psycoplankton

rock-bottom

The repository contains the notebook as well as python implementations of laguange models, from basic naive implementations to Transformers on a simple name dataset. more notebooks and files will be added regularly

rupee-vs-dollar-time-series-forecasting

An autoregressive forecasting implementation of a LSTM network, NBEATS architecture, ARIMA and SARIMAX regressions, and Autoformer architecture on rupee dollar exchange rates using pytorch, pytorch lightning, pytorch-forecasting, and GluonTS

sdo-hmi-los-magnetogram-images-

I have collected some images of around 20 Active Regions and separated them into training and test sets to run a CNN solar flare prediction model

skimlit-nlp-model

SkimLit is a Natural Language Processing based model which includes different embeddings and architectures for processing the PubMed dataset. Links to the papers which include the dataset and the details of the architectures are mentioned in the Colab notebook

wasserstein-graphgan