Computer Science

In an attempt to follow biological information representation and organization principles, the field of neuromorphic engineering is usually approached bottom-up, from the biophysical models to large-scale integration in silico. While ideal as experimentation platforms for cognitive computing and neuroscience, bottom-up neuromorphic processors have yet to demonstrate an efficiency advantage compared to specialized neural network accelerators for real-world problems. Top-down approaches aim at answering this difficulty by (i) starting from the applicative problem and (ii) investigating how to make the associated algorithms hardware-efficient and biologically-plausible. In order to leverage the data sparsity of spike-based neuromorphic retinas for adaptive edge computing and vision applications, we follow a top-down approach and propose SPOON, a 28-nm event-driven CNN (eCNN). It embeds online learning with only 16.8-% power and 11.8-% area overheads with the biologically-plausible direct random target projection (DRTP) algorithm. With an energy per classification of 313nJ at 0.6V and a 0.32-mm 2 area for accuracies of 95.3% (on-chip training) and 97.5% (off-chip training) on MNIST, we demonstrate that SPOON reaches the efficiency of conventional machine learning accelerators while embedding on-chip learning and being compatible with event-based sensors, a point that we further emphasize with N-MNIST benchmarking.

Neuromorphic computing with non-volatile memory (NVM) can significantly improve performance and lower energy consumption of machine learning tasks implemented using spike-based computations and bio-inspired learning algorithms. High voltages required to operate certain NVMs such as phase-change memory (PCM) can accelerate aging in a neuron's CMOS circuit, thereby reducing the lifetime of neuromorphic hardware. In this work, we evaluate the long-term, i.e., lifetime reliability impact of executing state-of-the-art machine learning tasks on a neuromorphic hardware, considering failure models such as negative bias temperature instability (NBTI) and time-dependent dielectric breakdown (TDDB). Based on such formulation, we show the reliability-performance trade-off obtained due to periodic relaxation of neuromorphic circuits, i.e., a stop-and-go style of neuromorphic computing.

The main goal of the multitasking optimization paradigm is to solve multiple and concurrent optimization tasks in a simultaneous way through a single search process. For attaining promising results, potential complementarities and synergies between tasks are properly exploited, helping each other by virtue of the exchange of genetic material. This paper is focused on Evolutionary Multitasking, which is a perspective for dealing with multitasking optimization scenarios by embracing concepts from Evolutionary Computation. This work contributes to this field by presenting a new multitasking approach named as Coevolutionary Variable Neighborhood Search Algorithm, which finds its inspiration on both the Variable Neighborhood Search metaheuristic and coevolutionary strategies. The second contribution of this paper is the application field, which is the optimal partitioning of graph instances whose connections among nodes are directed and weighted. This paper pioneers on the simultaneous solving of this kind of tasks. Two different multitasking scenarios are considered, each comprising 11 graph instances. Results obtained by our method are compared to those issued by a parallel Variable Neighborhood Search and independent executions of the basic Variable Neighborhood Search. The discussion on such results support our hypothesis that the proposed method is a promising scheme for simultaneous solving community detection problems over graphs.

This work reports a compact behavioral model for gated-synaptic memory. The model is developed in Verilog-A for easy integration into computer-aided design of neuromorphic circuits using emerging memory. The model encompasses various forms of gated synapses within a single framework and is not restricted to only a single type. The behavioral theory of the model is described in detail along with a full list of the default parameter settings. The model includes parameters such as a device's ideal set time, threshold voltage, general evolution of the conductance with respect to time, decay of the device's state, etc. Finally, the model's validity is shown via extensive simulation and fitting to experimentally reported data on published gated-synapses.

A multi-modal multi-objective optimization problem is a special kind of multi-objective optimization problem with multiple Pareto subsets. In this paper, we propose an efficient multi-modal multi-objective optimization algorithm based on the widely used MOEA/D algorithm. In our proposed algorithm, each weight vector has its own sub-population. With a clearing mechanism and a greedy removal strategy, our proposed algorithm can effectively preserve equivalent Pareto optimal solutions (i.e., different Pareto optimal solutions with same objective values). Experimental results show that our proposed algorithm can effectively preserve the diversity of solutions in the decision space when handling large-scale multi-modal multi-objective optimization problems.

The brain is known to be a highly complex, asynchronous dynamical system that is highly tailored to encode temporal information. However, recent deep learning approaches to not take advantage of this temporal coding. Spiking Neural Networks (SNNs) can be trained using biologically-realistic learning mechanisms, and can have neuronal activation rules that are biologically relevant. This type of network is also structured fundamentally around accepting temporal information through a time-decaying voltage update, a kind of input that current rate-encoding networks have difficulty with. Here we show that a large, deep layered SNN with dynamical, chaotic activity mimicking the mammalian cortex with biologically-inspired learning rules, such as STDP, is capable of encoding information from temporal data. We argue that the randomness inherent in the network weights allow the neurons to form groups that encode the temporal data being inputted after self-organizing with STDP. We aim to show that precise timing of input stimulus is critical in forming synchronous neural groups in a layered network. We analyze the network in terms of network entropy as a metric of information transfer. We hope to tackle two problems at once: the creation of artificial temporal neural systems for artificial intelligence, as well as solving coding mechanisms in the brain.

In real life, mostly problems are dynamic. Many algorithms have been proposed to handle the static problems, but these algorithms do not handle or poorly handle the dynamic environment problems. Although, many algorithms have been proposed to handle dynamic problems but still, there are some limitations or drawbacks in every algorithm regarding diversity of particles and tracking of already found optima. To overcome these limitations/drawbacks, we have proposed a new efficient algorithm to handle the dynamic environment effectively by tracking and locating multiple optima and by improving the diversity and convergence speed of algorithm. In this algorithm, a new method has been proposed which explore the undiscovered areas of search space to increase the diversity of algorithm. This algorithm also uses a method to effectively handle the overlapped and overcrowded particles. Branke has proposed moving peak benchmark which is commonly used MBP in literature. We also have performed different experiments on Moving Peak Benchmark. After comparing the experimental results with different state of art algorithms, it was seen that our algorithm performed more efficiently.

Data-driven evolutionary optimization has witnessed great success in solving complex real-world optimization problems. However, existing data-driven optimization algorithms require that all data are centrally stored, which is not always practical and may be vulnerable to privacy leakage and security threats if the data must be collected from different devices. To address the above issue, this paper proposes a federated data-driven evolutionary optimization framework that is able to perform data driven optimization when the data is distributed on multiple devices. On the basis of federated learning, a sorted model aggregation method is developed for aggregating local surrogates based on radial-basis-function networks. In addition, a federated surrogate management strategy is suggested by designing an acquisition function that takes into account the information of both the global and local surrogate models. Empirical studies on a set of widely used benchmark functions in the presence of various data distributions demonstrate the effectiveness of the proposed framework.

A typical deep neural network (DNN) has a large number of trainable parameters. Choosing a network with proper capacity is challenging and generally a larger network with excessive capacity is trained. Pruning is an established approach to reducing the number of parameters in a DNN. In this paper, we propose a framework for pruning DNNs based on a population-based global optimization method. This framework can use any pruning objective function. As a case study, we propose a simple but efficient objective function based on the concept of energy-based models. Our experiments on ResNets, AlexNet, and SqueezeNet for the CIFAR-10 and CIFAR-100 datasets show a pruning rate of more than 50% of the trainable parameters with approximately <5% and <1% drop of Top-1 and Top-5 classification accuracy, respectively.

Perceptual learning enables humans to recognize and represent stimuli invariant to various transformations and build a consistent representation of the self and physical world. Such representations preserve the invariant physical relations among the multiple perceived sensory cues. This work is an attempt to exploit these principles in an engineered system. We design a novel neural network architecture capable of learning, in an unsupervised manner, relations among multiple sensory cues. The system combines computational principles, such as competition, cooperation, and correlation, in a neurally plausible computational substrate. It achieves that through a parallel and distributed processing architecture in which the relations among the multiple sensory quantities are extracted from time-sequenced data. We describe the core system functionality when learning arbitrary non-linear relations in low-dimensional sensory data. Here, an initial benefit rises from the fact that such a network can be engineered in a relatively straightforward way without prior information about the sensors and their interactions. Moreover, alleviating the need for tedious modelling and parametrization, the network converges to a consistent description of any arbitrary high-dimensional multisensory setup. We demonstrate this through a real-world learning problem, where, from standard RGB camera frames, the network learns the relations between physical quantities such as light intensity, spatial gradient, and optical flow, describing a visual scene. Overall, the benefits of such a framework lie in the capability to learn non-linear pairwise relations among sensory streams in an architecture that is stable under noise and missing sensor input.