| 1. |
- Hemani, Ahmed, et al.
(författare)
-
Cell placement by self-organisation
- 1990
-
Ingår i: Neural Networks. - 0893-6080 .- 1879-2782. ; 3:4, s. 377-383
-
Tidskriftsartikel (refereegranskat)
|
|
| 2. |
- Karlholm, Jörgen
(författare)
-
Associative Memories with Short--Range Higher Order Couplings
- 1993
-
Ingår i: Neural Networks. - 0893-6080 .- 1879-2782. ; 6:3, s. 409-421
-
Tidskriftsartikel (refereegranskat)abstract
- A study of recurrent associative memories with exclusively short-range connections is presented. To increase the capacity, higher order couplings are used. We study capacity and pattern completion ability of networks consisting of units with binary (±1) output. Results show that perfect learning of random patterns is difficult for very short coupling ranges, and that the average expected capacities (allowing small errors) in these cases are much smaller than the theoretical maximum, 2 bits per coupling. However, it is also shown that by choosing ranges longer than certain limit sizes, depending on network size and order, we can come close to the theoretical capacity limit. We indicate that these limit sizes increase very slowly with net size. Thus, couplings to at least 28 and 36 neighbors suffice for second order networks with 400 and 90,000 units, respectively. From simulations it is found that even networks with coupling ranges below the limit size are able to complete input patterns with more than 10% errors. Especially remarkable is the ability to correct inputs with large local errors (part of the pattern is masked). We present a local learning algorithm for heteroassociation in recurrent networks without hidden units. The algorithm is used in a multinet system to improve pattern completion ability on correlated patterns.
|
|
| 3. |
- Bengtsson, Fredrik, et al.
(författare)
-
Cross-correlations between pairs of neurons in cerebellar cortex in vivo.
- 2013
-
Ingår i: Neural Networks. - : Elsevier BV. - 1879-2782 .- 0893-6080. ; 47:Dec.,06, s. 88-94
-
Tidskriftsartikel (refereegranskat)abstract
- In the present paper we apply a new neurophysiological technique to make single-electrode, dual loose-patch recordings from pairs of neuronal elements in the cerebellar cortex in vivo. The analyzed cell pairs consisted of an inhibitory molecular layer interneuron and a Purkinje cell (PC) or a Golgi cell and a granule cell, respectively. To detect the magnitude of the unitary inhibitory synaptic inputs we used histograms of the spike activity of the target cell, triggered by the spikes of the inhibitory cell. Using this analysis, we found that single interneurons had no detectable effect on PC firing, which could be explained by an expected very low synaptic weight of individual interneuron-PC connections. However, interneurons did have a weak delaying effect on the overall series of interspike intervals of PCs. Due to the very high number of inhibitory synapses on each PC, a concerted activation of the interneurons could still achieve potent PC inhibition as previously shown. In contrast, in the histograms of the Golgi cell-granule cell pairs, we found a weak inhibitory effect on the granule cell but only at the time period defined as the temporal domain of the slow IPSP previously described for this connection. Surprisingly, the average granule cell firing frequency sampled at one second was strongly modulated with a negative correlation to the overall firing level of the Golgi cell when the latter was modified through current injection via the patch pipette. These findings are compatible with that tonic inhibition is the dominant form of Golgi cell-granule cell inhibition in the adult cerebellum in vivo.
|
|
| 4. |
- Buda, Mateusz, et al.
(författare)
-
A systematic study of the class imbalance problem in convolutional neural networks
- 2018
-
Ingår i: Neural Networks. - : PERGAMON-ELSEVIER SCIENCE LTD. - 0893-6080 .- 1879-2782. ; 106, s. 249-259
-
Tidskriftsartikel (refereegranskat)abstract
- In this study, we systematically investigate the impact of class imbalance on classification performance of convolutional neural networks (CNNs) and compare frequently used methods to address the issue. Class imbalance is a common problem that has been comprehensively studied in classical machine learning, yet very limited systematic research is available in the context of deep learning. In our study, we use three benchmark datasets of increasing complexity, MNIST, CIFAR-10 and ImageNet, to investigate the effects of imbalance on classification and perform an extensive comparison of several methods to address the issue: oversampling, undersampling, two-phase training, and thresholding that compensates for prior class probabilities. Our main evaluation metric is area under the receiver operating characteristic curve (ROC AUC) adjusted to multi-class tasks since overall accuracy metric is associated with notable difficulties in the context of imbalanced data. Based on results from our experiments we conclude that (i) the effect of class imbalance on classification performance is detrimental; (ii) the method of addressing class imbalance that emerged as dominant in almost all analyzed scenarios was oversampling; (iii) oversampling should be applied to the level that completely eliminates the imbalance, whereas the optimal undersampling ratio depends on the extent of imbalance; (iv) as opposed to some classical machine learning models, oversampling does not cause overfitting of CNNs; (v) thresholding should be applied to compensate for prior class probabilities when overall number of properly classified cases is of interest.
|
|
| 5. |
- Chen, Zetao, et al.
(författare)
-
Bio-inspired homogeneous multi-scale place recognition
- 2015
-
Ingår i: Neural Networks. - : Elsevier. - 0893-6080 .- 1879-2782. ; 72, s. 48-61
-
Tidskriftsartikel (refereegranskat)abstract
- Robotic mapping and localization systems typically operate at either one fixed spatial scale, or over two, combining a local metric map and a global topological map. In contrast, recent high profile discoveries in neuroscience have indicated that animals such as rodents navigate the world using multiple parallel maps, with each map encoding the world at a specific spatial scale. While a number of theoretical-only investigations have hypothesized several possible benefits of such a multi-scale mapping system, no one has comprehensively investigated the potential mapping and place recognition performance benefits for navigating robots in large real world environments, especially using more than two homogeneous map scales. In this paper we present a biologically-inspired multi-scale mapping system mimicking the rodent multi-scale map. Unlike hybrid metric-topological multi-scale robot mapping systems, this new system is homogeneous, distinguishable only by scale, like rodent neural maps. We present methods for training each network to learn and recognize places at a specific spatial scale, and techniques for combining the output from each of these parallel networks. This approach differs from traditional probabilistic robotic methods, where place recognition spatial specificity is passively driven by models of sensor uncertainty. Instead we intentionally create parallel learning systems that learn associations between sensory input and the environment at different spatial scales. We also conduct a systematic series of experiments and parameter studies that determine the effect on performance of using different neural map scaling ratios and different numbers of discrete map scales. The results demonstrate that a multi-scale approach universally improves place recognition performance and is capable of producing better than state of the art performance compared to existing robotic navigation algorithms. We analyze the results and discuss the implications with respect to several recent discoveries and theories regarding how multi-scale neural maps are learnt and used in the mammalian brain.
|
|
| 6. |
- Ding, Yijie, et al.
(författare)
-
Shared subspace-based radial basis function neural network for identifying ncRNAs subcellular localization
- 2022
-
Ingår i: Neural Networks. - Oxford : Elsevier. - 0893-6080 .- 1879-2782. ; 156, s. 170-178
-
Tidskriftsartikel (refereegranskat)abstract
- Non-coding RNAs (ncRNAs) play an important role in revealing the mechanism of human disease for anti-tumor and anti-virus substances. Detecting subcellular locations of ncRNAs is a necessary way to study ncRNA. Traditional biochemical methods are time-consuming and labor-intensive, and computational-based methods can help detect the location of ncRNAs on a large scale. However, many models did not consider the correlation information among multiple subcellular localizations of ncRNAs. This study proposes a radial basis function neural network based on shared subspace learning (RBFNN-SSL), which extract shared structures in multi-labels. To evaluate performance, our classifier is tested on three ncRNA datasets. Our model achieves better performance in experimental results. © 2022 The Author(s)
|
|
| 7. |
- Foulsham, Tom, et al.
(författare)
-
Modeling eye movements in visual agnosia with a saliency map approach: Bottom–up guidance or top–down strategy?
- 2011
-
Ingår i: Neural Networks. - : Elsevier BV. - 1879-2782 .- 0893-6080. ; 24:6, s. 665-677
-
Tidskriftsartikel (refereegranskat)abstract
- Two recent papers (Foulsham, Barton, Kingstone, Dewhurst, & Underwood, 2009; Mannan, Kennard, & Husain, 2009) report that neuropsychological patients with a profound object recognition problem (visual agnosic subjects) show differences from healthy observers in the way their eye movements are controlled when looking at images. The interpretation of these papers is that eye movements can be modeled as the selection of points on a saliency map, and that agnosic subjects show an increased reliance on visual saliency, i.e., brightness and contrast in low-level stimulus features. Here we review this approach and present new data from our own experiments with an agnosic patient that quantifies the relationship between saliency and fixation location. In addition, we consider whether the perceptual difficulties of individual patients might be modeled by selectively weighting the different features involved in a saliency map. Our data indicate that saliency is not always a good predictor of fixation in agnosia: even for our agnosic subject, as for normal observers, the saliency–fixation relationship varied as a function of the task. This means that top–down processes still have a significant effect on the earliest stages of scanning in the setting of visual agnosia, indicating severe limitations for the saliency map model. Top–down, active strategies – which are the hallmark of our human visual system – play a vital role in eye movement control, whether we know what we are looking at or not.
|
|
| 8. |
- Fransén, Erik, 1962-
(författare)
-
Functional role of entorhinal cortex in working memory processing
- 2005
-
Ingår i: Neural Networks. - : Elsevier BV. - 0893-6080 .- 1879-2782. ; 18:9, s. 1141-1149
-
Tidskriftsartikel (refereegranskat)abstract
- Our learning and memory system has the challenge to work in a world where items to learn are dispersed in space and time. From the information extracted by the perceptual systems, the learning system must select and combine information. Both these operations may require a temporary storage where significance and correlations could be assessed. This work builds on the common hypothesis that hippocampus and subicular, entorhinal and parahippocampal/postrhinal areas are essential for the above-mentioned functions. We bring up two examples of models: the first one is modeling of in vivo and in vitro data from entorhinal cortex layer 11 of delayed match-to-sample working memory experiments, the second one studying mechanisms in theta rhythmicity in EC. In both cases, we discuss how cationic currents might be involved and relate their kinetics and pharmacology to behavioral and cellular experimental results.
|
|
| 9. |
|
|
| 10. |
- Green, Michael, et al.
(författare)
-
Exploring new possibilities for case based explanation of artificial neural network ensembles
- 2009
-
Ingår i: Neural Networks. - : Elsevier BV. - 1879-2782 .- 0893-6080. ; 22:1, s. 75-81
-
Tidskriftsartikel (refereegranskat)abstract
- Artificial neural network (ANN) ensembles have long suffered from a lack of interpretability. This has severely limited the practical usability of ANNs in settings where an erroneous decision can be disastrous. Several attempts have been made to alleviate this problem. Many of them are based on decomposing the decision boundary of the ANN into a set of rules. We explore and compare a set of new methods for this explanation process on two artificial data sets (Monks 1 and 3), and one acute coronary syndrome data set consisting of 861 electrocardiograms (ECG) collected retrospectively at the emergency department at Lund University Hospital. The algorithms managed to extract good explanations in more than 84% of the cases. More to the point, the best method provided 99% and 91% good explanations in Monks data 1 and 3 respectively. Also there was a significant overlap between the algorithms. Furthermore, when explaining a given ECG, the overlap between this method and one of the physicians was the same as the one between the two physicians in this study. Still the physicians were significantly, p-value <0.001, more similar to each other than to any of the methods. The algorithms have the potential to be used as an explanatory aid when using ANN ensembles in clinical decision support systems.
|
|
