Abstract. We describe a set of preliminary experiments to evolve spiking neural controllers for a vision-based mobile robot. All the evolutionary experiments are carried out on physical robots without human intervention. After discussing how to implement and interface these neurons with a physical robot, we show that evolution finds relatively quickly functional spiking controllers capable of navigating in irregularly textured environments without hitting obstacles using a very simple genetic encoding and fitness function. Neuroethological analysis of the network activity let us understand the functioning of evolved controllers and tell the relative importance of single neurons independently of their observed firing rate. Finally, a number of systematic lesion experiments indicate that evolved spiking controllers are very robust to synaptic strength decay that typically occurs in hardware implementations of spiking circuits. 1 Spiking Neural Circuits The great majority of biological neurons communicate by sending pulses along

We demonstrate that single-variable integrate-and-fire models can quantitatively capture the dynamics of a physiologically-detailed model for fast-spiking cortical neurons. Through a systematic set of approximations, we reduce the conductance based model to two variants of integrate-and-fire models. In the first variant (non-linear integrate-and-fire model), parameters depend on the instantaneous membrane potential whereas in the second variant, they depend on the time elapsed since the last spike (Spike Response Model). The direct reduction links features of the simple models to biophysical features of the full conductance based model. To quantitatively

Abstract. We continue here the study of the recently introduced spiking neural P systems, which mimic the way that neurons communicate with each other by means of short electrical impulses, identical in shape (voltage), but emitted at precise moments of time. The sequence of moments when a neuron emits a spike is called the spike train (of this neuron); by designating one neuron as the output neuron of a spiking neural P system Π, one obtains a spike train of Π. Given a specific way of assigning sets of numbers to spike trains of Π, we obtain sets of numbers computed by Π. In this way, spiking neural P systems become number computing devices. We consider a number of ways to assign (code) sets of numbers to (by) spike trains, and prove then computational completeness: the computed sets of numbers are exactly Turing computable sets. When the number of spikes present in the system is bounded, a characterization of semilinear sets of numbers is obtained. A number of research problems is also formulated. 1 1

Three different uses of a recurrent neural network (RNN) as a reservoir that is not trained but instead read out by a simple external classification layer have been described in the literature: Liquid State Machines (LSMs), Echo State Networks (ESNs) and the Backpropagation Decorrelation (BPDC) learning rule. Individual descriptions of these techniques exist, but a overview is still lacking. Here, we present a series of experimental results that compares all three implementations, and draw conclusions about the relation between a broad range of reservoir parameters and network dynamics, memory, node complexity and performance on a variety of benchmark tests with different characteristics. Next, we introduce a new measure for the reservoir dynamics based on Lyapunov exponents. Unlike previous measures in the literature, this measure is dependent on the dynamics of the reservoir in response to the inputs, and in the cases we tried, it indicates an optimal value for the global scaling of the weight matrix, irrespective of the standard measures. We also describe the Reservoir Computing Toolbox that was used for these experiments, which implements all the types of Reservoir Computing and allows the easy simulation of a wide range of reservoir topologies for a number of benchmarks.

Abstract. It is clear to all, after a moments thought, that nature has much we might be inspired by when designing our systems, for example: robustness, adaptability and complexity, to name a few. The implementation of bio-inspired systems in hardware has however been limited, and more often than not been more a matter of artistry than engineering. The reasons for this are many, but one of the main problems has always been the lack of a universal platform, and of a proper methodology for the implementation of such systems. The ideas presented in this paper are early results of a new research project, "Reconfigurable POEtic Tissue". The goal of the project is the development of a hardware platform capable of implementing systems inspired by all the three major axes (phylogenesis, ontogenesis, and epigenesis) of bio-inspiration, in digital hardware. 1

Abstract—We present a transmitter for a scalable multiple-access inter-chip link that communicates binary activity between two-dimensional arrays fabricated in deep submicrometer CMOS. Transmission is initiated by active cells but cells are not read individually. An entire row is read in parallel; this increases communication capacity with integration density. Access is random but not inequitable. A row is not reread until all those waiting are serviced; this increases parallelism as more of its cells become active in the mean time. Row and column addresses identify active cells but they are not transmitted simultaneously. The row address is followed sequentially by a column address for each active cell; this cuts pad count in half without sacrificing capacity. We synthesized an asynchronous implementation by performing a series of program decompositions, starting from a high-level description. Links using this design have been implemented successfully in

Spiking neurons axe models for the computational units in biological neural systems where information is considered to be encoded mainly in the temporal patterns of their activity. In a network of spiking neurons a new set of paxameters becomes relevant which has no counterpaxt in traditional neural network models: the time that a pulse needs to travel through a connection between two neurons (also known as delay of a connection). It is known that these delays axe tuned in biological neural systems through a vaxiety of mechanisms. In this

Experimental data show that biological synapses behave quite differently from the symbolic synapses in all common artificial neural network models. Biological synapses are

In search for small universal computing devices of various types, we consider here the case of spiking neural P systems (SN P systems), in two versions: as devices computing functions and as devices generating sets of numbers. We start with the first case and we produce a universal spiking neural P system with 84 neurons. If a slight generalization of the used rules is adopted, namely, we allow rules for producing simultaneously several spikes, then a considerable improvement, to 49 neurons, is obtained. For SN P systems used as generators of sets of numbers, we find a universal system with restricted rules having 76 neurons, and one with extended rules having 50 neurons.

We describe a model and implementation of evolutionary spiking neurons for embedded microcontrollers with few bytes of memory and very low power consumption. The approach is tested with an autonomous microrobot of less than 1 in 3 that evolves the ability to move in a small maze without human intervention and external computers. Considering the very large diffusion, small size, and low cost of embedded microcontrollers, the approach described here could find its way in several intelligent devices with sensors and/or actuators, as well as in smart credit cards. Artificial Spiking Circuits Most biological neurons communicate by sending pulses across connections to other neurons. The pulse is also known as “spike ” to indicate its short and transient nature. Neurons are affected by incoming spikes and generate a spike when their membrane potential becomes larger than a threshold. Spike generation is followed by a short “refractory period ” during which the neuron cannot generate another spike. Computational models of spiking neurons are attracting increasing interest in engineering and computer science (Maas & Bishop 1999). On the one hand, computer simulations of spiking networks can help to address specific questions in neuroscience, such as how biological neurons communicate with each other (Koenig, Engel, & Singer 1996; Rieke et al. 1997). On the other hand, a better understanding of spiking neurons is leading to the development of new neuromorphic devices (Horiuchi 2001), some of which may replace lesioned fibers or sensory organs. In addition, we argue that networks of spiking neurons represent suitable control systems for autonomous behavioral systems, 1 such as situated autonomous robots, because temporal patterns of sensory-motor events may be captured and exploited more efficiently (i.e., with fewer neurons or with higher probability) by the intrinsic time-dependent dynamics of spiking neurons than by 1 They certainly showed to be excellent control systems for biological organisms! other connectionist models (Rumelhart, McClelland, &