A robust biologically plausible implementation of ICA-like learning
نویسندگان
چکیده
We present a model that can perform ICA-like learning by simple, local, biologically plausible rules. By combining synaptic learning with homeostatic regulation of neuron properties and adaptive lateral inhibition, the neural network can robustly learn Gabor-like receptive fields from natural images. With spatially localized inhibitory connections, a topographic map can be achieved. Additionally, the network can solve the Földiák bars problem, a classical nonlinear ICA task.
منابع مشابه
Independent Component Analysis in Spiking Neurons
Although models based on independent component analysis (ICA) have been successful in explaining various properties of sensory coding in the cortex, it remains unclear how networks of spiking neurons using realistic plasticity rules can realize such computation. Here, we propose a biologically plausible mechanism for ICA-like learning with spiking neurons. Our model combines spike-timing depend...
متن کاملReservoir Computing and Slow Feature Analysis for Autonomous Map Learning and Self-localization of Small Mobile Robots
Small mobile robots must be able to self-localize in their environment in order to accomplish tasks. Biological systems (e.g., rats) have efficient and robust localization abilities provided by the so called, place cells, which are found in the hippocampus of rodents and primates (these cells encode locations of the animal’s environment). This work seeks to model these place cells by employing ...
متن کاملUnsupervised Learning in Reservoir Computing: Modeling Hippocampal Place Cells for Small Mobile Robots
Biological systems (e.g., rats) have efficient and robust localization abilities provided by the so called, place cells, which are found in the hippocampus of rodents and primates (these cells encode locations of the animal’s environment). This work seeks to model these place cells by employing three (biologically plausible) techniques: Reservoir Computing (RC), Slow Feature Analysis (SFA), and...
متن کاملTowards a Biologically Plausible and Efficient Reinforcement Learning Agent
The primary goal of this degree project was to evaluate a selection of biologically plausible reinforcement learning (RL) agents. An agent was assumed to be biologically plausible if it could be constructed using a biologically plausible model of learning. Such a model had to be realizable using an artificial neural network (ANN) with a learning rule that could be implemented within biological ...
متن کاملFeasibility of Incremental Learning in Biologically Plausible Networks
The feasibility of incremental learning within a feed-forward network is examined under the constraint of biologically plausible connectivity. A randomly connected network (of physiologically plausible global connection probability) is considered under the assumption of a local connection probability which decays with distance between nodes. The representation of the function XOR is chosen as a...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2009