sreelekshmyselvin

AquilaDB-Examples

Usecase Examples for AquilaDB

bark

🔊 Text-Prompted Generative Audio Model

Data-Science--Cheat-Sheet

Cheat Sheets

elasticbert

Information Retrieval system built by BERT and elasticsearch

fastbook

Draft of the fastai book

l1-Trend-Filtering

The proposed system uses l1 trend filter as a image denoising technique. l1 trend filter was initially developed for one dimensional signals . In this work we are extending the idea for color images

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

Mask_RCNN

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

pdf-difference-finder

A PDF comparison utility in Python.

STOCK-PRICE-PREDICTION-FOR-NSE-USING-DEEP-LEARNING-MODELS

Financial time series analysis and prediction have become an important area of re- search in today's world. Designing and pricing securities, construction of portfolios and other risk management strategies depends on the prediction of financial time se- ries. A financial time series often involve large dataset with complex interaction among themselves. A proper analysis of this data will give the investor better gains, but the existing methodologies focus on linear models (AR, MA, ARMA, ARIMA) and non- linear models (ARCH, GARCH, TAR). These models are not capable of identifying the complex interactions and latent dynamics existing within the data. Applying Deep learning methods to these types of data will give more accurate results than the existing methods. Deep learning architectures can identify the hidden patterns in the data and is also capable of exploiting the interactions existing within the data, which is, at least not possible by the existing financial models. The proposed work uses four different deep learning architectures (RNN, LSTM, CNN, and MLP) for predicting the minute wise stock price for NSE listed companies and compares the performance of the mod- els. The proposed method uses a sliding window based approach for predicting future values on a short-term basis. The performance of the models was quantified using error percentage.

sreelekshmyselvin/STOCK-PRICE-PREDICTION-FOR-NSE-USING-DEEP-LEARNING-MODELS

Financial time series analysis and prediction have become an important area of re- search in today's world. Designing and pricing securities, construction of portfolios and other risk management strategies depends on the prediction of financial time se- ries. A financial time series often involve large dataset with complex interaction among themselves. A proper analysis of this data will give the investor better gains, but the existing methodologies focus on linear models (AR, MA, ARMA, ARIMA) and non- linear models (ARCH, GARCH, TAR). These models are not capable of identifying the complex interactions and latent dynamics existing within the data. Applying Deep learning methods to these types of data will give more accurate results than the existing methods. Deep learning architectures can identify the hidden patterns in the data and is also capable of exploiting the interactions existing within the data, which is, at least not possible by the existing financial models. The proposed work uses four different deep learning architectures (RNN, LSTM, CNN, and MLP) for predicting the minute wise stock price for NSE listed companies and compares the performance of the mod- els. The proposed method uses a sliding window based approach for predicting future values on a short-term basis. The performance of the models was quantified using error percentage.

sreelekshmyselvin/pdf-difference-finder

A PDF comparison utility in Python.

sreelekshmyselvin/AquilaDB-Examples

Usecase Examples for AquilaDB

sreelekshmyselvin/bark

🔊 Text-Prompted Generative Audio Model

sreelekshmyselvin/Data-Science--Cheat-Sheet

Cheat Sheets

sreelekshmyselvin/elasticbert

Information Retrieval system built by BERT and elasticsearch

sreelekshmyselvin/fastbook

Draft of the fastai book

sreelekshmyselvin/l1-Trend-Filtering

The proposed system uses l1 trend filter as a image denoising technique. l1 trend filter was initially developed for one dimensional signals . In this work we are extending the idea for color images

sreelekshmyselvin/LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

sreelekshmyselvin/Mask_RCNN

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

sreelekshmyselvin/MoTIF

Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments

sreelekshmyselvin/nlp-tutorial

Natural Language Processing Tutorial for Deep Learning Researchers

sreelekshmyselvin/nlp_paper_summaries

✍️ A carefully curated list of NLP paper summaries

sreelekshmyselvin/PaddleNLP

👑 Easy-to-use and powerful NLP library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis and 🖼 Diffusion AIGC system etc.

sreelekshmyselvin/pdftotree

[UNMAINTAINED] :evergreen_tree: A tool for parsing PDF documents into a hierarchical, HTML-like tree.

sreelekshmyselvin/PGDDA-Assignments

sreelekshmyselvin/projects

💝 Example projects for various NLP tasks with datasets, scripts and results

sreelekshmyselvin/rasa

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

sreelekshmyselvin/SecLists

SecLists is the security tester's companion. It's a collection of multiple types of lists used during security assessments, collected in one place. List types include usernames, passwords, URLs, sensitive data patterns, fuzzing payloads, web shells, and many more.

sreelekshmyselvin/shap

A game theoretic approach to explain the output of any machine learning model.

sreelekshmyselvin/transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.