vikram-mm Goto Github PK

android-malware-detection

cs388-nlp

Course Assignments

go-back-n-arq-

Go-Back-N ARQ using raw sockets. The mac addresses of the sender and receiver is used for sending the frames.

guidedproofreading

Guided Proofreading of Automatic Segmentations for Connectomics

id3-decision-tree

The ID3 algorithm for building a decision tree is implemented. data_preProcess.cpp gets the input in the csv file to the required format. This has to be given as the input to the id3_general.cpp. Clustering of input can be done if the attributes take continuous values to improve the accuracy.

libo

code.fun.do

libo_final

code.fun.do

machine-learning-models-python

This includes my course assignments.

mammogram-classification

Classification of augmented mammogram samples into normal,benign or malignant using CNN.

multimodal-image-retrieval

Explores early fusion and late fusion approaches for Multimodal medical Image Retrieval

spiking-neural-network---theano-framework

Spiking neural networks are biologically plausible CNNs which learn through a temporally dependent learning method known as Spike Time Dependant Plasticity (STDP)- an alternate to gradient descent. This repository contains layers built on top of Lasagne layers for spiking neural networks. This is the first implementation of spiking neural networks in any tensor based framework to the best of my knowledge. The various layers can be found in snn.py for dense layer and snn_conv.py for other layers. These layers are to be processed for each time step which is done using the Theano scan as a quick hack - in the snn class. The results can be found the ppt. Further details on how to use the code will be put up after later.

theano-lasagne-cnn-cifar10

This repository contains the code for implementing a simple CNN using lasagne. There are three folders : nooby, standard and binary activation. Nooby contains a naive and simple code for implementing a CNN. Standard contains a more structured way of implementing a CNN which makes the code more flexible to modifications. Binary activation contains a CNN which uses a tailor made op for activation function - this returns 1 or 0 based on the sign of the input, also the gradient is simply passed through if the input is between 0 and 1, else the gradient is killed.

traffic-sign-detection-yolo

Ongoing minor project

trial

vikram-mm.github.io