5 skills found
michelin / TorchSOMTorchSOM is a PyTorch-based library for training Self-Organizing Maps (SOMs), a model trained in an unsupervised manner, that can be used for clustering, dimensionality reduction and data visualization. It is designed to be scalable and user-friendly.
HITS-AIN / PINKParallelized rotation and flipping INvariant Kohonen maps
leobispo / SomSOM - Self organizing Map is a Swing application that implements the Self organizing map algorithm. Self-organizing map (SOM) is a type of artificial neural network that is trained using unsupervised learning to produce low-dimensional representation of the training samples while preserving the topological properties of the input space. Self-Organizing Map showing US Congress voting patterns visualized in Synapse Self-Organizing Map showing US Congress voting patterns visualized in Synapse This makes SOM useful for visualizing low-dimensional views of high-dimensional data, akin to multidimensional scaling. The model was first described as an artificial neural network by the Finnish professor Teuvo Kohonen, and is sometimes called a Kohonen map. Like most artificial neural networks, SOMs operate in two modes: training and mapping. Training builds the map using input examples. It is a competitive process, also called vector quantization. Mapping automatically classifies a new input vector.
BharadwajYellapragada / Effective Handwritten Digit Recognition Using Deep Convolution Neural NetworkThis is code implementation for a paper on "Effective Handwritten Digit Recognition using Deep Convolution Neural Network". This paper proposed a simple neural network approach towards handwritten digit recognition using convolution. With machine learning algorithms like KNN, SVM/SOM, recognizing digits is considered as one of the unsolvable tasks due to its distinctiveness in the style of writing. In this paper, Convolution Neural Networks are implemented with an MNIST dataset of 70000 digits with 250 distinct forms of writings. The proposed method achieved 98.51% accuracy for real-world handwritten digit prediction with less than 0.1 % loss on training with 60000 digits while 10000 under validation.
fruitzzx / Printed Digits ClassificationThis project presents a hybrid algorithm for training RBF network based on K-means and SOM. The algorithm consists of a proposed clustering algorithm to position the RBF center and givens least squares to estimate the weights. The aim of this experiment is to recognize printed digits (1-4) using the hybrid model. In the meanwhile, KNN and MLP with Scaled Conjugate Gradient will be implemented in order to show the comparative of different models according to the experiments.
