| 1. |
- Berg, H., et al.
(författare)
-
Automatic design of pulse coupled neurons for image segmentation
- 2008
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 71:10-12, s. 1980-1993
-
Tidskriftsartikel (refereegranskat)abstract
- Automatic Design of Algorithms through Evolution (ADATE) is a program synthesis system that creates recursive programs in a functional language with automatic invention of recursive help functions and self-adaptive optimization of numerical values. We implement a neuron in a pulse coupled neural network (PCNN) as a recursive function in the ADATE language and then use ADATE to automatically evolve better PCNN neurons for image segmentation. Our technique is generally applicable for automatic improvement of most image processing algorithms and neural computing methods. It may be used either to generally improve a given implementation or to tailor that implementation to a specific problem, which with respect to image segmentation for example can be road following for autonomous vehicles or infrared image segmentation for heat seeking missiles that are to distinguish the heat source of the target from flares.
|
|
| 2. |
- Cartling, Bo
(författare)
-
On the implicit acquisition of a context-free grammar by a simple recurrent neural network
- 2008
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 71:7-9, s. 1527-1537
-
Tidskriftsartikel (refereegranskat)abstract
- The performance of a simple recurrent neural network on the implicit acquisition of a context-free grammar is re-examined and found to be significantly higher than previously reported by Elman. This result is obtained although the previous work employed it multilayer extension of the basic form of simple recurrent network and restricted the complexity of training and test corpora. The high performance is traced to a well-organized internal representation of the grammatical elements, as probed by a principal-component analysis of the hidden-layer activities. From the next-symbol-prediction performance on sentences not present in the training corpus, it capacity of generalization is demonstrated.
|
|
| 3. |
- Cürüklü, Baran, et al.
(författare)
-
A model of the summation pools within the layer 4 (area 17)
- 2005
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 65, s. 167-172
-
Tidskriftsartikel (refereegranskat)abstract
- We propose a developmental model of the summation pools within the layer 4. The model is based on the modular structure of the neocortex and captures some of the known properties of layer 4. Connections between the orientation minicolumns are developed during exposure to visual input. Excitatory local connections are dense and biased towards the iso-orientation domain. Excitatory long-range connections are sparse and target all orientation domains equally. Inhibition is local. The summation pools are elongated along the orientation axis. These summation pools can facilitate weak and poorly tuned LGN input and explain improved visibility as an effect of enlargement of a stimulus.
|
|
| 4. |
- Dimitrakakis, Christos, 1975, et al.
(författare)
-
Online adaptive policies for ensemble classifiers
- 2005
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 64:1-4 SPEC. ISS., s. 211-221
-
Tidskriftsartikel (refereegranskat)abstract
- Ensemble algorithms can improve the performance of a given learning algorithm through the combination of multiple base classifiers into an ensemble. In this paper, we attempt to train and combine the base classifiers using an adaptive policy. This policy is learnt through a Q-learning inspired technique. Its effectiveness for an essentially supervised task is demonstrated by experimental results on several UCI benchmark databases. © 2005 Elsevier B.V. All rights reserved.
|
|
| 5. |
- Fransén, Erik, 1962-
(författare)
-
A synapse which can switch from inhibitory to excitatory and back
- 2005
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 65, s. 39-45
-
Tidskriftsartikel (refereegranskat)abstract
- Co-release of transmitters has recently been observed at synapse terminals and can even be a combination such as glutamate and GABA. A second recent experimental finding is a short-term synaptic plasticity, which depends on postsynaptic depolarization releasing a dendritic transmitter, which affects presynaptic release probability. In this work we are investigating the functional consequences for a synapse if it had both co-release and conditioning depression. If initially the GABA component is larger than the glutamate component, the synapse has an inhibitory net effect. However, if the postsynaptic cell is conditioned, the GABA component will be suppressed yielding an excitatory synapse.
|
|
| 6. |
- Fransén, Erik, 1962-
(författare)
-
Neural response profile design : Reducing epileptogenic activity by modifying neuron responses to synchronized input using novel potassium channels obtained by parameter search optimization
- 2007
-
Ingår i: Neurocomputing. - AMSTERDAM : ELSEVIER SCIENCE. - 0925-2312 .- 1872-8286. ; 70:10-12, s. 1630-1634
-
Tidskriftsartikel (refereegranskat)abstract
- Neurons obtain their dynamical electrical characteristics by a set of ion channels. These properties may not only affect the function of the neuron and the local network it forms part of, but it may also eventually affect behavior. We were interested to study whether epileptogenic activity could be reduced by adding an ion channel. In this work, we used computational search techniques to optimize ion channel properties for the goal of modifying neural response characteristics. Our results show that this type of parameter search is possible and reasonably efficient. Successful searches were generated using the direct method PRAXIS, and by systematic searches in low-dimensional sub-spaces. We also report on unsuccessful searches using a simplex-type method, a gradient-based method, and attempts to reduce goal function evaluation time. Importantly, using this search strategy, our study has shown that it is possible to change a neuron's characteristics selectively with regard to response to degree of synchronicity in synaptic input.
|
|
| 7. |
- Hellgren Kotaleski, Jeanette, et al.
(författare)
-
The role of background synaptic noise in striatal fast spiking interneurons
- 2005
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 65, s. 727-732
-
Tidskriftsartikel (refereegranskat)abstract
- Striatal fast spiking (FS) interneurons provide inhibition to each other as well as to medium spiny projection (SP) neurons. They exhibit up-states synchronously with SP neurons, and receive GABAergic and AMPA synaptic input during both up- and down-states. The synaptic input during down-states can be considered noise and might affect detection of up-states. We investigate what role this background noise might play for up-state firing in a 127 compartment FS model neuron. The model has Na, KDr and KA conductances, and is activated through AMPA and GABA synapses. The model's response to current injection and synaptic inputs resembled experimental data. We show that intermediate levels of noise neither facilitates nor degrades the ability of the FS neuron model to detect up-states.
|
|
| 8. |
- Hjorth, Johannes, et al.
(författare)
-
The significance of gap junction location in striatal fast spiking interneurons
- 2007
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 70:10-12, s. 1887-1891
-
Tidskriftsartikel (refereegranskat)abstract
- Fast spiking (FS) interneurons in the striatunt are hypothesised to control spike timing in the numerous medium spiny (MS) projection neurons by inhibiting or delaying firing in the MS neurons. The FS neurons are connected to each other through electrical gap junctions. This might synchronise the FS neurons, leading to increased influence on target neurons. Here, we explore the possible difference between proximal and distal gap junction locations. Somatic and distal dendritic gap junctions with equal effective coupling coefficient, as defined for steady-state somatic inputs, showed significantly different effective coupling coefficient with transient inputs. However, the ability to synchronise spiking in pairwise coupled FS neurons, which received synaptic inputs as during striatal up-state periods, was as effective with distal gap junctions as with proximal ones. Proximal gap junctions, however, caused synchronisation within a more precise time window.
|
|
| 9. |
- Huss, Mikael, et al.
(författare)
-
Modelling self-sustained rhythmic activity in lamprey hemisegmental networks
- 2006
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 69:10-12, s. 1097-1102
-
Tidskriftsartikel (refereegranskat)abstract
- Recent studies of the lamprey spinal cord have shown that hemisegmental preparations can display rhythmic activity in response to a constant input drive. This activity is believed to be generated by a network of recurrently connected excitatory interneurons. A recent study found and characterized self-sustaining rhythmic activity-locomotor bouts-after brief electrical stimulation of hemisegmental preparations. The mechanisms behind the bouts are still unclear. We have developed a computational model of the hemisegmental network. The model addresses the possible involvement of NMDA, AMPA, acetylcholine, and metabotropic glutamate receptors as well as axonal delays in locomotor bouts.
|
|
| 10. |
- Huss, Mikael, et al.
(författare)
-
Tonically driven and self-sustaining activity in the lamprey hemicord : when can they co-exist?
- 2007
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 70:10-12, s. 1882-1886
-
Tidskriftsartikel (refereegranskat)abstract
- In lamprey hernisegmental preparations, two types of rhythmic activity are found: slower tonically driven activity which varies according to the external drive, and faster, more stereotypic activity that arises after a transient electrical stimulus. We present a simple conceptual model where a bistable excitable system can exhibit the two states. We then show that a neuronal network model can display the desired characteristics, given that synaptic dynamics-facilitation and saturation-are included. The model behaviour and its dependence on key parameters are illustrated. We discuss the relevance of our model to the lamprey locomotor system.
|
|
