Encoding the Temporal Statistics of Markovian Sequences of Stimuli in Recurrent Neuronal Networks
نویسندگان
چکیده
Encoding, storing, and recalling a temporal sequence of stimuli in a neuronal network can be achieved by creating associations between pairs of stimuli that are contiguous in time. This idea is illustrated by studying the behavior of a neural network model with binary neurons and binary stochastic synapses. The network extracts in an unsupervised manner the temporal statistics of the sequence of input stimuli. When a stimulus triggers the recalling process, the statistics of the output patterns reflects those of the input. If the sequence of stimuli is generated through a Markov process, then the network dynamics faithfully reproduces all the transition probabilities.
منابع مشابه
معرفی شبکه های عصبی پیمانه ای عمیق با ساختار فضایی-زمانی دوگانه جهت بهبود بازشناسی گفتار پیوسته فارسی
In this article, growable deep modular neural networks for continuous speech recognition are introduced. These networks can be grown to implement the spatio-temporal information of the frame sequences at their input layer as well as their labels at the output layer at the same time. The trained neural network with such double spatio-temporal association structure can learn the phonetic sequence...
متن کاملReceptive Field Encoding Model for Dynamic Natural Vision
Introduction: Encoding models are used to predict human brain activity in response to sensory stimuli. The purpose of these models is to explain how sensory information represent in the brain. Convolutional neural networks trained by images are capable of encoding magnetic resonance imaging data of humans viewing natural images. Considering the hemodynamic response function, these networks are ...
متن کاملSynchronization criteria for T-S fuzzy singular complex dynamical networks with Markovian jumping parameters and mixed time-varying delays using pinning control
In this paper, we are discuss about the issue of synchronization for singular complex dynamical networks with Markovian jumping parameters and additive time-varying delays through pinning control by Takagi-Sugeno (T-S) fuzzy theory.The complex dynamical systems consist of m nodes and the systems switch from one mode to another, a Markovian chain with glorious transition probabili...
متن کاملTowards an effective multi-map self organizing recurrent neuronal network
This paper presents a multi-map joint self-organizing architecture able to represent non-markovian temporal sequences. The proposed architecture is inspired by previous works based on dynamic neural fields. It provides a faster and easier to handle architecture making it easier to scale to higher dimensional machine learning problems.
متن کاملEncoding in Balanced Networks: Revisiting Spike Patterns and Chaos in Stimulus-Driven Systems
Highly connected recurrent neural networks often produce chaotic dynamics, meaning their precise activity is sensitive to small perturbations. What are the consequences of chaos for how such networks encode streams of temporal stimuli? On the one hand, chaos is a strong source of randomness, suggesting that small changes in stimuli will be obscured by intrinsically generated variability. On the...
متن کامل