radu-dogaru's repositories
ELM-super-fast
Python implementation of ELM - with optimized speed on MKL-based platforms; Described in conference paper: Radu Dogaru, Ioana Dogaru, "Optimization of extreme learning machines for big data applications using Python", COMM-2018; Allows quantization of weight parameters in both layers and introduces a new and very effective hidden layer nonlinearity (absolute value)
LightWeight_Binary_CNN_and_ELM_Keras
Light weight convolutional neural networks and Keras based ELM (extreme learning machine)
fast-fhn-rd-cnn-simulators
Four simulators for reaction-diffusion cellular nonlinear networks running on Google COLAB
LB-CNN-compact-and-fast-binary-including-very-fast-ELM
A framework to train and optimize light convolutional networks, also includes a very fast Chainer/Cupy training using extreme learning machine as output layer
NL-CNN-a-compact-fast-trainable-convolutional-neural-net
A fast yet light convolutional neural network model suitable for small/medium input image sizes (up to 64x64)
Fast-Support-Vector-Classifier
Implementation of the FSVC algorithm (Octave and Matlab MEX compiled)
Binary_conv_CNN_models
Some CNN models where weights in the convolution layers are {-1,1} while weights in the output layers are fixed point integers (for finite number of bits)
NL-CNN-RDT-based-sound-classification-
Models and their evaluation for paper: Radu Dogaru and Ioana Dogaru "RD-CNN: A Compact and Efficient Convolutional Neural Net for Sound Classification ", ISETC-2020
numpyCNN
A simple vectorized implementation of a Convolutional Neural Network in plain Numpy && more
Super_Fast_Vector_Classifier
A Python implementation of the algorithm described in paper Radu Dogaru, Ioana Dogaru, "Optimized Super Fast Support Vector Classifiers Using Python and Acceleration of RBF Computations", (2018) ; There is no output layer learning only a relatively fast selection of support vectors in a RBF-layer optimized for speed. Faster than SVM