The temporal Kohönen map

By G. Chappell, John G. Taylor. 1993

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Lifelong learning of human actions with deep neural network self-organization (2017, methodology): “The first example was the Temporal Kohonen Map (TKM, Chappell & Taylor, 1993) where the distance of a recurrent neuron wi from the input sequence (x(t −n), . . . , x(t)) with similarity measure dW (e.g. the Euclidean distance) is computed as d̃i(t) = α · dW (x(t),wi) + (1 − α) · d̃i(t − 1),…”
Neural methods for non-standard data (2004, background): “Most unsupervised recursive models have been proposed only for temporal data, and they obey a simple dynamics given by leaky integrators or traveling waves [16, 74, 104].”
Strong systematicity through sensorimotor conceptual grounding: an unsupervised, developmental approach to connectionist sentence processing (2012, methodology): “Architectures such as the temporal Kohonen map (TKM; Chappell and Taylor 1993) make use of leaky integrators that allow the learning rule to factor recently winning nodes into subsequent best-matching node calculations.”
Time Series Prediction with the Self-Organizing Map: A Review (2007, background): “More recently, several temporal vector quantization algorithms have been proposed [10, 33, 2, 48, 59, 1], specially within the field of neural networks, that aim at performing better than static clustering methods when dealing with time series data.”
Forecasting the CATS benchmark with the Double Vector Quantization method (2007, background): “Models and prediction methodologies have been proposed by statisticians, mathematicians and engineers, as well as people from econometrics and more recently from the neural network community.”
Incremental Unsupervised Time Series Analysis Using Merge Growing Neural Gas (2009, background): “Temporal Kohonen Map (TKM) [11], Recurrent SOM (RSOM) [12], Recursive SOM (RecSOM) [13], SOM for structured data (SOM-SD) [14], Merge SOM (MSOM) and Merge Neural Gas (MNG) [1] represent popular recursive models which have been applied in several applications [15–19].”
Human motion assessment in real time using recurrent self-organization (2016, methodology): “However, in the TKM there is no explicit back-reference to previous map activity, i.e. the context is only implicitly represented by the weights.”
SARDNET: A Self-Organizing Feature Map for Sequences (1994, background): “Recently, Chappel and Taylor (1993) proposed the Temporal Kohonen Map (TKM) architecture for classifying sequences.”
Merge SOM for temporal data (2005, methodology): “Key words: Self-organizing map, temporal Kohonen map, sequence processing, recurrent models, neural gas, fractal encoding, finite automata, speaker identification, DNA splice site detection.”