shentqlf / softmaxcpp Goto Github PK
View Code? Open in Web Editor NEWThis project forked from michaeloneill/softmaxcpp
This project forked from michaeloneill/softmaxcpp
The modules here relate to the softmax classifier model in my mini-project report "Linear classification models applied to the classification of hand-written digits", submitted towards the degree of MPhil in Scientific Computing and Machine Learning, University of Cambridge. The MNIST data files should be downloaded from http://cis.jhu.edu/~sachin/digit/digit.html and organised by digit into a folder MNISTdata, with MNISTdata/data0 corresponding to digit 0 etc. all the way up to digit 9. The project uses the c++ armadillo linear algebra library. The included Makefile has the required linker flags to this library for running the code on the LSC computers. Before compiling: Set the tunable parameters in main.C to generate results for a specific test case. These parameters have been labelled with self-explanatory names. To compile the program: make Softmax To run it: ./Softmax Numerical gradient checking can be performed by toggling on/off the DEBUG_GRADIENTS macro in Softmax.C. The file plotSoftmax.py can be used to generate all the plots. Note that output data files for the plotting of learning curves and validation curves will only be produced if the TUNING macro in main.C is set to true.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.