Neural activity sequences are ubiquitous in the brain and play pivotal roles in functions such as long-term memory formation and motor control. While conditions for storing and reactivating individual sequences have been thoroughly characterized, it remains unclear how multiple sequences may interact when activated simultaneously in recurrent neural networks. This question is especially relevant for weak sequences, comprised of fewer neurons, competing against strong sequences. Using a non-linear rate -based and a spiking model with discrete, pre-configured assemblies, we demonstrate that weak sequences can compensate for their competitive disadvantage either by increasing excitatory connections between subsequent assemblies or by cooperating with other co-active sequences. Further, our models suggest that such cooperation can negatively affect sequence speed unless subsequently active assemblies are paired. Our analysis characterizes the conditions for successful sequence progression in isolated, competing, and cooperating assembly sequences, and identifies the distinct contributions of recurrent and feed-forward projections. This proof-of-principle study shows how even disadvantaged sequences can be prioritized for reactivation, a process which has recently been implicated in hippocampal memory processing.

Spiking neural network simulations are a central tool in Computational Neuroscience, Artificial Intelligence, and Neuromorphic Engineering research. A broad range of simulators and software frameworks for such simulations exist with different target application areas. Among these, PymoNNto is a recent Python-based toolbox for spiking neural network simulations that emphasizes the embedding of custom code in a modular and flexible way. While PymoNNto already supports GPU implementations, its backend relies on NumPy operations. Here we introduce PymoNNtorch, which is natively implemented with PyTorch while retaining PymoNNto's modular design. Furthermore, we demonstrate how changes to the implementations of common network operations in combination with PymoNNtorch's native GPU support can offer speed-up over conventional simulators like NEST, ANNarchy, and Brian 2 in certain situations. Overall, we show how PymoNNto's modular and flexible design in combination with PymoNNtorch's GPU acceleration and optimized indexing operations facilitate research and development of spiking neural networks in the Python programming language.

The human brain constantly learns and rapidly adapts to new situations by integrating acquired knowledge and experiences into memory. Developing this capability in machine learning models is considered an important goal of AI research since deep neural networks perform poorly when there is limited data or when they need to adapt quickly to new unseen tasks. Meta-learning models are proposed to facilitate quick learning in low-data regimes by employing absorbed information from the past. Although some models have recently been introduced that reached high-performance levels, they are not biologically plausible. We have proposed a bio-plausible meta-learning model inspired by the hippocampus and the prefrontal cortex using spiking neural networks with a reward-based learning system. Our proposed model includes a memory designed to prevent catastrophic forgetting, a phenomenon that occurs when meta-learning models forget what they have learned as soon as the new task begins. Also, our new model can easily be applied to spike-based neuromorphic devices and enables fast learning in neuromorphic hardware. The final analysis will discuss the implications and predictions of the model for solving few-shot classification tasks. In solving these tasks, our model has demonstrated the ability to compete with the existing state-of-the-art meta-learning techniques.

The plasticity of the conduction delay between neurons plays a fundamental role in learning temporal features that are essential for processing videos, speech, and many high-level functions. However, the exact underlying mechanisms in the brain for this modulation are still under investigation. Devising a rule for precisely adjusting the synaptic delays could eventually help in developing more efficient and powerful brain-inspired computational models. In this article, we propose an unsupervised bioplausible learning rule for adjusting the synaptic delays in spiking neural networks. We also provide the mathematical proofs to show the convergence of our rule in learning spatiotemporal patterns. Furthermore, to show the effectiveness of our learning rule, we conducted several experiments on random dot kinematogram and a subset of DVS128 Gesture data sets. The experimental results indicate the efficiency of applying our proposed delay learning rule in extracting spatiotemporal features in an STDP-based spiking neural network.

Theory of Mind is referred to the ability of inferring other's mental states, and it plays a crucial role in social cognition and learning. Biological evidences indicate that complex circuits are involved in this ability, including the mirror neuron system. The mirror neuron system influences imitation abilities and action understanding, leading to learn through observing others. To simulate this imitative learning behavior, a Theory-of-Mind-based Imitative Reinforcement Learning (ToM-based ImRL) framework is proposed. Employing the bio-inspired spiking neural networks and the mechanisms of the mirror neuron system, ToM-based ImRL is a bio-inspired computational model which enables an agent to effectively learn how to act in an interactive environment through observing an expert, inferring its goals, and imitating its behaviors. The aim of this paper is to review some computational attempts in modeling ToM and to explain the proposed ToM-based ImRL framework which is tested in the environment of River Raid game from Atari 2600 series.

The growing interest in brain-inspired computational models arises from the remarkable problem-solving efficiency of the human brain. Action recognition, a complex task in computational neuroscience, has received significant attention due to both its intricate nature and the brain's exceptional performance in this area. Nevertheless, current solutions for action recognition either exhibit limitations in effectively addressing the problem or lack the necessary biological plausibility. Deep neural networks, for instance, demonstrate acceptable performance but deviate from biological evidence, thereby restricting their suitability for brain-inspired computational studies. On the other hand, the majority of brain-inspired models proposed for action recognition exhibit significantly lower effectiveness compared to deep models and fail to achieve human-level performance. This deficiency can be attributed to their disregard for the underlying mechanisms of the brain. In this article, we present an effective brain-inspired computational model for action recognition. We equip our model with novel biologically plausible mechanisms for spiking neural networks that are crucial for learning spatio-temporal patterns. The key idea behind these new mechanisms is to bridge the gap between the brain's capabilities and action recognition tasks by integrating key biological principles into our computational framework. Furthermore, we evaluate the performance of our model against other models using a benchmark dataset for action recognition, DVS-128 Gesture. The results show that our model outperforms previous biologically plausible models and competes with deep supervised models.

Meta-learning techniques enable quick learning of new tasks by using few samples with utilizing prior knowledge learned from previous tasks. Gradient-based models are widely used because of their simplicity and ability to solve a wide range of problems. However, they only succeed in solving tasks with a very similar structure since they adapt the model with a shared meta-parameter across all tasks. In recent years, some models have been proposed to enhance the gradient-based models to deal with task uncertainty and heterogeneity via sharing knowledge among similar tasks by using task clustering. Nevertheless, the high-dimensional parameter space of gradient-based models hinders them from achieving their full potential in low-data regimes. Bayesian meta-learning algorithms address this issue by learning a data-dependent latent generative representation of model parameters. Our proposed model bypasses the aforementioned limitations by leveraging Bayesian algorithms as well as clustering input tasks. The final analysis demonstrates the effectiveness of the proposed model for few-shot image classification problems.

The human visual system contains a hierarchical sequence of modules that take part in visual perception at superordinate, basic, and subordinate categorization levels. During the last decades, various computational models have been proposed to mimic the hierarchical feed-forward processing of visual cortex, but many critical characteristics of the visual system, such actual neural processing and learning mechanisms, are ignored. Pursuing the line of biological inspiration, we propose a computational model for object recognition in different categorization levels, in which a spiking neural network equipped with the reinforcement learning rule is used as a module at each categorization level. Each module solves the object recognition problem at each categorization level, solely based on the earliest spike of class-specific neurons at its last layer, without using any external classifier. According to the required information at each categorization level, the relevant band-pass filtered images are utilized. The performance of our proposed model is evaluated by various appraisal criteria with three benchmark datasets and significant improvement in recognition accuracy of our proposed model is achieved in all experiments.

The human visual system contains a hierarchical sequence of modules that take part in visual perception at superordinate, basic, and subordinate categorisation levels. The top-down signals facilitate the bottom-up processing of visual information in the cortical analysis of object recognition. We propose a novel computational model for object recognition in different categorisation levels, which mimics the effects of top-down signals in the hierarchical processing of the visual system. The top-down signal is incorporated in bottom-up processing of input image to increase the biological plausibility of our model as well as its efficiency for the object recognition in different categorisation levels. The top-down signals provide a pre-knowledge about the input space, which can help to solve the complex object recognition tasks. The performance of our model is evaluated by various appraisal criteria with three benchmark datasets and significant improvement in recognition accuracy of our proposed model is achieved in all experiments.

The plasticity of the conduction delay between neurons plays a fundamental role in learning. However, the exact underlying mechanisms in the brain for this modulation is still an open problem. Understanding the precise adjustment of synaptic delays could help us in developing effective brain-inspired computational models in providing aligned insights with the experimental evidence. In this paper, we propose an unsupervised biologically plausible learning rule for adjusting the synaptic delays in spiking neural networks. Then, we provided some mathematical proofs to show that our learning rule gives a neuron the ability to learn repeating spatio-temporal patterns. Furthermore, the experimental results of applying an STDP-based spiking neural network equipped with our proposed delay learning rule on Random Dot Kinematogram indicate the efficacy of the proposed delay learning rule in extracting temporal features.

Application of deep convolutional spiking neural networks (SNNs) to artificial intelligence (AI) tasks has recently gained a lot of interest since SNNs are hardware-friendly and energy-efficient. Unlike the non-spiking counterparts, most of the existing SNN simulation frameworks are not practically efficient enough for large-scale AI tasks. In this paper, we introduce SpykeTorch, an open-source high-speed simulation framework based on PyTorch. This framework simulates convolutional SNNs with at most one spike per neuron and the rank-order encoding scheme. In terms of learning rules, both spike-timing-dependent plasticity (STDP) and reward-modulated STDP (R-STDP) are implemented, but other rules could be implemented easily. Apart from the aforementioned properties, SpykeTorch is highly generic and capable of reproducing the results of various studies. Computations in the proposed framework are tensor-based and totally done by PyTorch functions, which in turn brings the ability of just-in-time optimization for running on CPUs, GPUs, or Multi-GPU platforms.

•We used a bio-inspired deep convolutional spiking neural network with latency-coding.•We trained the low (resp. top) layers with STDP (resp. reward-modulated STDP).•Accuracy was 97.2% on MNIST, without requiring an external classifier.•Reward-modulated STDP favors diagnostic features, while STDP favors frequent ones.•The proposed neuron-based decision-making layer is suitable for energy-efficient hardware implementation.

The primate visual system has inspired the development of deep artificial neural networks, which have revolutionized the computer vision domain. Yet these networks are much less energy-efficient than their biological counterparts, and they are typically trained with backpropagation, which is extremely data-hungry. To address these limitations, we used a deep convolutional spiking neural network (DCSNN) and a latency-coding scheme. We trained it using a combination of spike-timing-dependent plasticity (STDP) for the lowest layers and reward-modulated STDP (R-STDP) for the highest ones. In short, with R-STDP a correct (resp. incorrect) decision leads to STDP (resp. anti-STDP). This approach led to an accuracy of 97.2% on MNIST, without requiring an external classifier. In addition, we demonstrated that R-STDP extracts features that are diagnostic for the task at hand, and discards the other ones, whereas STDP extracts any feature that repeats. Finally, our approach is biologically plausible, hardware friendly, and energy-efficient.

Reinforcement learning (RL) has recently regained popularity with major achievements such as beating the European game of Go champion. Here, for the first time, we show that RL can be used efficiently to train a spiking neural network (SNN) to perform object recognition in natural images without using an external classifier. We used a feedforward convolutional SNN and a temporal coding scheme where the most strongly activated neurons fire first, while less activated ones fire later, or not at all. In the highest layers, each neuron was assigned to an object category, and it was assumed that the stimulus category was the category of the first neuron to fire. If this assumption was correct, the neuron was rewarded, i.e., spike-timing-dependent plasticity (STDP) was applied, which reinforced the neuron's selectivity. Otherwise, anti-STDP was applied, which encouraged the neuron to learn something else. As demonstrated on various image data sets (Caltech, ETH-80, and NORB), this reward-modulated STDP (R-STDP) approach has extracted particularly discriminative visual features, whereas classic unsupervised STDP extracts any feature that consistently repeats. As a result, R-STDP has outperformed STDP on these data sets. Furthermore, R-STDP is suitable for online learning and can adapt to drastic changes such as label permutations. Finally, it is worth mentioning that both feature extraction and classification were done with spikes, using at most one spike per neuron. Thus, the network is hardware friendly and energy efficient.

Previous studies have shown that spike-timing-dependent plasticity (STDP) can be used in spiking neural networks (SNN) to extract visual features of low or intermediate complexity in an unsupervised manner. These studies, however, used relatively shallow architectures, and only one layer was trainable. Another line of research has demonstrated – using rate-based neural networks trained with back-propagation – that having many layers increases the recognition robustness, an approach known as deep learning. We thus designed a deep SNN, comprising several convolutional (trainable with STDP) and pooling layers. We used a temporal coding scheme where the most strongly activated neurons fire first, and less activated neurons fire later or not at all. The network was exposed to natural images. Thanks to STDP, neurons progressively learned features corresponding to prototypical patterns that were both salient and frequent. Only a few tens of examples per category were required and no label was needed. After learning, the complexity of the extracted features increased along the hierarchy, from edge detectors in the first layer to object prototypes in the last layer. Coding was very sparse, with only a few thousands spikes per image, and in some cases the object category could be reasonably well inferred from the activity of a single higher-order neuron. More generally, the activity of a few hundreds of such neurons contained robust category information, as demonstrated using a classifier on Caltech 101, ETH-80, and MNIST databases. We also demonstrate the superiority of STDP over other unsupervised techniques such as random crops (HMAX) or auto-encoders. Taken together, our results suggest that the combination of STDP with latency coding may be a key to understanding the way that the primate visual system learns, its remarkable processing speed and its low energy consumption. These mechanisms are also interesting for artificial vision systems, particularly for hardware solutions.

BACKGROUND:Although different protein-protein physical interaction (PPI) datasets exist for Escherichia coli, no common methodology exists to integrate these datasets and extract reliable modules reflecting the existing biological process and protein complexes. Naïve Bayesian formula is the highly accepted method to integrate different PPI datasets into a single weighted PPI network, but detecting proper weights in such network is still a major problem.RESULTS:In this paper, we proposed a new methodology to integrate various physical PPI datasets into a single weighted PPI network in a way that the detected modules in PPI network exhibit the highest similarity to available functional modules. We used the co-expression modules as functional modules, and we shown that direct functional modules detected from Gene Ontology terms could be used as an alternative dataset. After running this integrating methodology over six different physical PPI datasets, orthologous high-confidence interactions from a related organism and two AP-MS PPI datasets gained high weights in the integrated networks, while the weights for one AP-MS PPI dataset and two other datasets derived from public databases have converged to zero. The majority of detected modules shaped around one or few hub protein(s). Still, a large number of highly interacting protein modules were detected which are functionally relevant and are likely to construct protein complexes.CONCLUSIONS:We provided a new high confidence protein complex prediction method supported by functional studies and literature mining.

Finding an effective measure to predict a more accurate RNA secondary structure is a challenging problem. In the last decade, an experimental method, known as selective [Formula: see text]-hydroxyl acylation analyzed by primer extension (SHAPE), was proposed to measure the tendency of forming a base pair for almost all nucleotides in an RNA sequence. These SHAPE reactivities are then utilized to improve the accuracy of RNA structure prediction. Due to a significant impact of SHAPE reactivity and in order to reduce the experimental costs, we propose a new model called HL-k-mer. This model simulates the SHAPE reactivity for each nucleotide in an RNA sequence. This is done by fetching the SHAPE reactivities for all sub-sequences of length k (k-mers) appearing in helix and loop regions. For evaluating the quality of simulated SHAPE data, ESD-Fold method is used based on the SHAPE data simulated by the HL-k-mer model ([Formula: see text]). Also, for further evaluation of simulated SHAPE data, three different methods are employed. We also extend this model to simulate the SHAPE data for the RNA pseudoknotted structure. The results indicate that the average accuracies of prediction using the SHAPE data simulated by our models (for [Formula: see text]) are higher compared to the experimental SHAPE data.

The human visual system contains a hierarchical sequence of modules that take part in visual perception at different levels of abstraction, i.e., superordinate, basic, and subordinate levels. One important question is to identify the ``entry" level at which the visual representation is commenced in the process of object recognition. For a long time, it was believed that the basic level had a temporal advantage over two others. This claim has been challenged recently. Here we used a series of psychophysics experiments, based on a rapid presentation paradigm, as well as two computational models, with bandpass filtered images of five object classes to study the processing order of the categorization levels. In these experiments, we investigated the type of visual information required for categorizing objects in each level by varying the spatial frequency bands of the input image. The results of our psychophysics experiments and computational models are consistent. They indicate that the different spatial frequency information had different effects on object categorization in each level. In the absence of high frequency information, subordinate and basic level categorization are performed less accurately, while the superordinate level is performed well. This means that low frequency information is sufficient for superordinate level, but not for the basic and subordinate levels. These finer levels rely more on high frequency information, which appears to take longer to be processed, leading to longer reaction times. Finally, to avoid the ceiling effect, we evaluated the robustness of the results by adding different amounts of noise to the input images and repeating the experiments. As expected, the categorization accuracy decreased and the reaction time increased significantly, but the trends were the same. This shows that our results are not due to a ceiling effect. The compatibility between our psychophysical and computational results suggests that the temporal advantage of the superordinate (resp. basic) level to basic (resp. subordinate) level is mainly due to the computational constraints (the visual system processes higher spatial frequencies more slowly, and categorization in finer levels depends more on these higher spatial frequencies).

Deep convolutional neural networks (DCNNs) have attracted much attention recently, and have shown to be able to recognize thousands of object categories in natural image databases. Their architecture is somewhat similar to that of the human visual system: both use restricted receptive fields, and a hierarchy of layers which progressively extract more and more abstracted features. Yet it is unknown whether DCNNs match human performance at the task of view-invariant object recognition, whether they make similar errors and use similar representations for this task, and whether the answers depend on the magnitude of the viewpoint variations. To investigate these issues, we benchmarked eight state-of-the-art DCNNs, the HMAX model, and a baseline shallow model and compared their results to those of humans with backward masking. Unlike in all previous DCNN studies, we carefully controlled the magnitude of the viewpoint variations to demonstrate that shallow nets can outperform deep nets and humans when variations are weak. When facing larger variations, however, more layers were needed to match human performance and error distributions, and to have representations that are consistent with human behavior. A very deep net with 18 layers even outperformed humans at the highest variation level, using the most human-like representations.