COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |

University of Cambridge > Talks.cam > Computational Neuroscience > A three-threshold learning rule approaches the maximal capacity of recurrent neural networks

## A three-threshold learning rule approaches the maximal capacity of recurrent neural networksAdd to your list(s) Download to your calendar using vCal - Alireza Alemi, Politecnico di Torino (Italy)
- Wednesday 24 June 2015, 11:30-12:00
- Cambridge University Engineering Department, CBL, BE-438 (http://learning.eng.cam.ac.uk/Public/Directions).
If you have a question about this talk, please contact Guillaume Hennequin. Understanding the theoretical foundations of how memories are encoded and retrieved in neural populations is a central challenge in neuroscience. A popular theoretical scenario for modeling memory function is the attractor neural network scenario, whose prototype is the Hopfield model. The model simplicity and the locality of the synaptic update rules come at the cost of a poor storage capacity, compared with the capacity achieved with perceptron learning algorithms. Here, by transforming the perceptron learning rule, we present an on-line learning rule for a recurrent neural network that achieves near-maximal storage capacity without an explicit supervisory error signal, relying only upon locally accessible information. The fully-connected network consists of excitatory binary neurons with plastic recurrent connections and non-plastic inhibitory feedback stabilizing the network dynamics; the memory patterns to be memorized are presented on-line as strong afferent currents, producing a bimodal distribution for the neuron synaptic inputs. Synapses corresponding to active inputs are modified as a function of the value of the local fields with respect to three thresholds. Above the highest threshold, and below the lowest threshold, no plasticity occurs. In between these two thresholds, potentiation/depression occurs when the local field is above/below an intermediate threshold. We simulated and analyzed a network of binary neurons implementing this rule and measured its storage capacity for different sizes of the basins of attraction. The storage capacity obtained through numerical simulations is shown to be close to the value predicted by analytical calculations. We also measured the dependence of capacity on the strength of external inputs. Finally, we quantified the statistics of the resulting synaptic connectivity matrix, and found that both the fraction of zero weight synapses and the degree of symmetry of the weight matrix increase with the number of stored patterns. This talk is part of the Computational Neuroscience series. ## This talk is included in these lists:- All Talks (aka the CURE list)
- Biology
- Biology
- CBL important
- CamBridgeSens
- Cambridge Centre for Data-Driven Discovery (C2D3)
- Cambridge Neuroscience Seminars
- Cambridge University Engineering Department, CBL, BE-438 (http://learning.eng.cam.ac.uk/Public/Directions)
- Cambridge talks
- Chris Davis' list
- Computational Neuroscience
- Computational and Biological Learning Seminar Series
- Featured lists
- Guy Emerson's list
- Hanchen DaDaDash
- Inference Group Journal Clubs
- Inference Group Summary
- Information Engineering Division seminar list
- Interested Talks
- Life Science
- Life Science Interface Seminars
- Life Sciences
- Life Sciences
- ME Seminar
- Neuroscience
- Neuroscience Seminars
- Neuroscience Seminars
- Quantum Matter Journal Club
- Required lists for MLG
- Stem Cells & Regenerative Medicine
- TQS Journal Clubs
- Trust & Technology Initiative - interesting events
- bld31
- custom
- dh539
- my_list
- ndk22's list
- rp587
- yk373's list
Note that ex-directory lists are not shown. |
## Other listsTalks related to atmosphere and ocean dynamics and climate science Assessment Principles Talk by Bashir Saoudi## Other talksThe MMHT view of the proton Cohomology of the moduli space of curves CANCELLED in solidarity with strike action: Permanent Sovereignty over Natural Resources and the Unsettling of Mainstream Narratives of International Legal History “Structural Biology and Chemistry of Histone Deacetylases in Human Disease and Drug Discover Domain Uncertainty Quantification SciBarHealth: Heart Month |