Perception as Bayesian inference
Perception as Bayesian inference
Probabilistic interpretation of population codes
Neural Computation
Neural representation of probabilistic information
Neural Computation
Bayesian spiking neurons i: Inference
Neural Computation
Bayesian spiking neurons ii: Learning
Neural Computation
Online learning with hidden markov models
Neural Computation
IEEE Transactions on Information Theory
IEEE Transactions on Signal Processing
| Hi-index | 0.00 |
Bayesian spiking neurons BSNs provide a probabilistic interpretation of how neurons perform inference and learning. Online learning in BSNs typically involves parameter estimation based on maximum-likelihood expectation-maximization ML-EM which is computationally slow and limits the potential of studying networks of BSNs. An online learning algorithm, fast learning FL, is presented that is more computationally efficient than the benchmark ML-EM for a fixed number of time steps as the number of inputs to a BSN increases e.g., 16.5ï戮 times faster run times for 20 inputs. Although ML-EM appears to converge 2.0 to 3.6ï戮 times faster than FL, the computational cost of ML-EM means that ML-EM takes longer to simulate to convergence than FL. FL also provides reasonable convergence performance that is robust to initialization of parameter estimates that are far from the true parameter values. However, parameter estimation depends on the range of true parameter values. Nevertheless, for a physiologically meaningful range of parameter values, FL gives very good average estimation accuracy, despite its approximate nature. The FL algorithm therefore provides an efficient tool, complementary to ML-EM, for exploring BSN networks in more detail in order to better understand their biological relevance. Moreover, the simplicity of the FL algorithm means it can be easily implemented in neuromorphic VLSI such that one can take advantage of the energy-efficient spike coding of BSNs.