Jonathan A. Tepper

Learn More
We present a neural network for real-time learning and mapping of patterns using an external performance indicator. In a non-stationary environment where new patterns are introduced over time, the learning process utilises a novel snap-drift algorithm that performs fast, convergent, minimalist learning (snap) when the overall network performance is poor and(More)
Connectionist parsers are neural-network-based systems (see Boxes 1 and 2) designed to process words or their syntactic types (tags) to produce a correct syntactic interpretation, or parse, of complete sentences. Parsers vary greatly in the way in which they tackle syntactic processing, and this is reflected in their modularity (or non-modularity) and in(More)
We describe a deterministic shift-reduce parsing model that combines the advantages of connectionism with those of traditional symbolic models for parsing realistic sub-domains of natural language. It is a modular system that learns to annotate natural language texts with syntactic structure. The parser acquires its linguistic knowledge directly from(More)
This paper presents a novel connectionist memory-rule based model capable of learning the finite-state properties of an input language from a set of positive examples. The model is based upon an unsupervised recurrent self-organizing map with laterally interconnected neurons. A derivation of functional-equivalence theory is used that allows the model to(More)
A neural network architecture is introduced for real-time learning of input sequences using external performance feedback. Some aspects of Adaptive Resonance Theory (ART) networks [1] are applied because they are able to function in a fast real-time adaptive active network environment where user requests and new proxylets (services) are constantly being(More)
The vanishing gradients problem inherent in Simple Recurrent Networks (SRN) trained with back-propagation, has led to a significant shift towards the use of Long Short-term Memory (LSTM) and Echo State Networks (ESN), which overcome this problem through either second order error-carousel schemes or different learning algorithms respectively. This paper(More)
This paper provides the most complete evidence to date on the importance of monetary aggregates as a policy tool in an inflation forecasting experiment. Every possible definition of 'money' in the USA is being considered for the full data period (1960 – 2006), in addition to two different approaches to constructing the benchmark asset, using the most(More)
  • 1