Pinned Repositories
AdventOfCode2022
ASCOM.DSLR
ASCOM Driver for DSLR Cameras
astrophotograpython
An open-source, simple, astrophotography post-processing library.
Automated-Bing-Searches
Simple chrome extension to run a number of Bing searches by just clicking a button. This is useful for collecting Microsoft Reward Points.
basic-pitch
A lightweight yet powerful audio-to-MIDI converter with pitch bend detection
BingRewards
Bing! Rewards Automation script - earn rewards automatically
Chat-with-Document-s-using-ChatGPT-API-and-Text-Embedding
Chat with Document(s) using ChatGPT API and Text Embedding
chat-your-data
convnetjs
Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.
Python-ChatGPT-Voice-Assistant
A ChatGPT voice assistant using speech input and output, leveraging Gradio, OpenAI API, and Whisper ASR, to perform versatile roles in a user-friendly interface.
k1vd's Repositories
k1vd/epicycler
Create epicycle animations.
k1vd/SVMPath
SVMPath - Regularization Path for the Support Vector Machines
k1vd/astrophotograpython
An open-source, simple, astrophotography post-processing library.
k1vd/Gensim-LSI-Word-Similarities
Generate word-word similarities from Gensim's latent semantic indexing (Python)
k1vd/Relevance-Ranking-using-Latent-Semantic-Indexing--from-scratch-
Latent Semantic Analysis Introduction: An information retrieval technique patented in 1988. In the context of its application to information retrieval, it is sometimes called Latent Semantic Indexing (LSI). LSI allows a search engine to determine what a page is about outside of specifically matching search query text. It looks at “Themes” instead of “Keywords”. Linear Algebra techniques used in the project: Singular Value Decomposition, Cosine Similarity, Matrix properties. Dataset: “Sci.space” news group from 20 news groups dataset, available in the Scikit-Learn library. It contains 400 news articles related to space. SVD (Singular Value Decomposition): SVD is a matrix decomposition algorithm, it decomposes a matrix into 3 matrices which are a set to transformations. Decomposition leads to an orthogonal matrix U, Diagonal matrix S and a Diagonal Matrix V. This is the best possible transformation of a matrix. In this decomposition method we are looking for a set of orthonormal basis in the row space that when multiplied by the original matrix goes to an orthonormal basis in the column space.Av1 = σ1u1 Av2 = σ2u2
k1vd/Latent-Semantic-Indexing
Vanilla implementation of a basic search engine that uses LSI to index documents and retrieve results to search queries. The repository also includes the document set used for experimentation, the benchmark queries and the results obtained on them.
k1vd/lsi-document-similarity
Find similar documents using Latent Semantic Indexing
k1vd/BingRewards
Bing! Rewards Automation script - earn rewards automatically