kstrassheim Goto Github PK
Type: User
Location: Zürich
Type: User
Location: Zürich
We present our concept of a new type of Active-Learning for Deep Learning with NLP text classification and experimentally prove its performance against Random Sampling as well as its runtime performance on the Security Threat dataset from CySecAlert. These new Active Learning algorithms are based on Sentence-BERT and BERTopic clustering algorithms with allow us to generate fixed length tokens for whole sentences to make them comparable to each other. Further the Tokens are Clustered using K-Means or HDBScan to get diverse clusters to pick the samples out of them.
By using capacitive pressure sensors inside a seat this application is able to retreive the signal and measure the respiratory rate out of its sinus frequency, by using 3 different algorithms (Discrete Fourier Transformation, Continuous Cut Count, Discrete single period)
My notes / works on deep learning from Coursera
Notes, programming assignments and quizzes from all courses within the Coursera Deep Learning specialization offered by deeplearning.ai: (i) Neural Networks and Deep Learning; (ii) Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization; (iii) Structuring Machine Learning Projects; (iv) Convolutional Neural Networks; (v) Sequence Models
This is a content and schema crawler tool to receive, update and import various kinds of data into a Onprem or Cloud based SQLServer or Azure-Synapse-Analysis (Azure Datawarehouse SQLServer). As source it supports SQLServer Tables, ODATA Endpoints, CSV Files or Excel Files. For multiple sources it can run in parallel mode where it would make a thread for each connection. The speciality of this crawler is that it creates the target tables by himself using the additional info from source.json. In case of Azure-Synapse-Analysis it would estimate the distribution type and keys. The syncing works completely without SQL Transactions by using a consistency correction algorithm for very frequent fact tables. There are 5 Syncing Algorithms (see Manual/Insert) which can be selected as well as one Update Algorithm.
This web-app shows the functionality of the model-agnostic explainable-ai engine LIME on 3 common deep learning text classifiers (BERT, LSTM, TFIDF-NN) for fake news detection.
This app transforms and shows geo-data points (lon, lat) for selected countries on custom mercator maps (pixels)
A simple whiteboard for pictures to enable cooperative working. The purpose was to show the possibility of an intuitive, real-time, responsive and progressive web-application without buttons and text.
some self build data science predictors
The frontend for the usermanagement web
Simple test app for webpack configurations
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.