Learn More
We propose a biologically plausible learning scheme which enables a system to classify patterns based on the presentation of one single example. During a learning mode, the system recognizes whether a category for a presented pattern has been instantiated before, or whether it must be classiied as unknown. In this case a new category is created(More)
We propose a biologically plausible learning scheme which enables a system to classify patterns based on the presentation of one single example. During a learning mode, the system recognizes whether a category for a presented pattern has been instantiated before, or whether it must be classiied as unknown. In this case a new category is created(More)
We studied competitive learning dynamics in diierent time scale regimes of learning. By rst assuming that learning is fast, we develop a self-organizing linear pattern classiier which can categorize patterns based on the presentation of single examples. The system can recognize patterns as "unknown" and autonomously instantiate new categories. Competition(More)
The development of complex artiicial vision systems raises the problem of evaluating the performance of constituting modules for purpose of optimization. We propose two methods for the visualization of modules' performance which can be applied to vision systems in neural architectu-res. These are characterized by several levels of coupled feature detecting(More)
  • 1