Algorithms used to train neural networks and to turn data into vectors that networks can use. The perceptron is the earliest trained network unit, backpropagation computes how each weight should change to reduce error, stochastic gradient descent applies those changes to small batches of data, and Word2Vec learns vector representations of words. The self-organizing map and the detection transformer apply related ideas to clustering and to finding objects in images.
Browse By
Neural Network Training and Representation Algorithms
Filter Results4 entries
Sources
Knowledge distillation (Wikipedia)
Has Member: Knowledge distillation, LeadQuote, Has Member: Knowledge distillation, Lead
In machine learning, knowledge distillation or model distillation is the process of transferring knowledge from a large model to a smaller one.
Wikipedia: Perceptron
Has Member: Perceptron Algorithm, LeadQuote, Has Member: Perceptron Algorithm, Lead
In machine learning, the perceptron is an algorithm for supervised learning of binary classifiers.
Backpropagation, Wikipedia
Has Member: Backpropagation Algorithm, LeadQuote, Has Member: Backpropagation Algorithm, Lead
In machine learning, backpropagation is a gradient computation method commonly used for training a neural network in computing parameter updates.
Self-organizing map (Wikipedia)
Has Member: Self-Organizing Map Algorithm, LeadQuote, Has Member: Self-Organizing Map Algorithm, Lead
A self-organizing map (SOM) or self-organizing feature map (SOFM) is an unsupervised machine learning technique used to produce a low-dimensional (typically two-dimensional) representation of a higher-dimensional data set while preserving the topological structure of the data.
Reader Challenges (0)
No disputes yet. Spotted an error or a better source? Open the first one.
Sign in to dispute this or suggest a correction.