Learning binary or real-valued time-series via spike-timing dependent plasticity
نویسنده
چکیده
A dynamic Boltzmann machine (DyBM) has been proposed as a model of a spiking neural network, and its learning rule of maximizing the log-likelihood of given time-series has been shown to exhibit key properties of spike-timing dependent plasticity (STDP), which had been postulated and experimentally confirmed in the field of neuroscience as a learning rule that refines the Hebbian rule. Here, we relax some of the constraints in the DyBM in a way that it becomes more suitable for computation and learning. We show that learning the DyBM can be considered as logistic regression for binary-valued time-series. We also show how the DyBM can learn real-valued data in the form of a Gaussian DyBM and discuss its relation to the vector autoregressive (VAR) model. The Gaussian DyBM extends the VAR by using additional explanatory variables, which correspond to the eligibility traces of the DyBM and capture long term dependency of the time-series. Numerical experiments show that the Gaussian DyBM significantly improves the predictive accuracy over VAR.
منابع مشابه
Spike timing dependent plasticity: mechanisms, significance, and controversies
Long-term modification of synaptic strength is one of the basic mechanisms of memory formation and activity-dependent refinement of neural circuits. This idea was purposed by Hebb to provide a basis for the formation of a cell assembly. Repetitive correlated activity of pre-synaptic and post-synaptic neurons can induce long-lasting synaptic strength modification, the direction and extent of whi...
متن کاملOptimal Spike-Timing Dependent Plasticity for Precise Action Potential Firing in Supervised Learing
In timing-based neural codes, neurons have to emit action potentials at precise moments in time. We use a supervised learning paradigm to derive a synaptic update rule that optimizes via gradient ascent the likelihood of postsynaptic firing at one or several desired firing times. We find that the optimal strategy of up and down regulating synaptic efficacies depends on the relative timing betwe...
متن کاملSpike timing dependent plasticity: mechanisms, significance, and controversies
Long-term modification of synaptic strength is one of the basic mechanisms of memory formation and activity-dependent refinement of neural circuits. This idea was purposed by Hebb to provide a basis for the formation of a cell assembly. Repetitive correlated activity of pre-synaptic and post-synaptic neurons can induce long-lasting synaptic strength modification, the direction and extent of whi...
متن کاملOptimal Spike-Timing Dependent Plasticity for Precise Action Potential Firing
In timing-based neural codes, neurons have to emit action potentials at precise moments in time. We use a supervised learning paradigm to derive a synaptic update rule that optimizes via gradient ascent the likelihood of postsynaptic firing at one or several desired firing times. We find that the optimal strategy of upand downregulating synaptic efficacies can be described by a two-phase learni...
متن کاملA Model of Spike - Timing Dependent Plasticity : One or Two
[PDF] [Full Text] [Abstract] , May 1, 2007; 19 (5): 1362-1399. Neural Comput. P. A. Appleby and T. Elliott Multispike Interactions in a Stochastic Model of Spike-Timing-Dependent Plasticity [PDF] [Full Text] [Abstract] , September 5, 2007; 27 (36): 9711-9720. J. Neurosci. J.-t. Lu, C.-y. Li, J.-P. Zhao, M.-m. Poo and X.-h. Zhang Interneurons Depends on Target Cell Type Spike-Timing-Dependen...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1612.04897 شماره
صفحات -
تاریخ انتشار 2016