This paper presents a new approach to neural modeling based on the idea of using an automated method to optimize the parameters of a synaptic learning rule The synaptic modi cation rule is considered as a parametric function This function has local inputs and is the same in many neurons We can use standard optimization methods to select appropriate parameters for a given type of task We also pr...

In this chapter, the authors describe the intrinsic needs to effectively integrate interactive vocal conversations over heterogeneous networks including packetand circuitbased networks. The requirement to harmonize transport networks is discussed and a foreseen architecture multi -operators and -services is presented. Moreover, envisaged remedies to the ever increasing network complexity are al...

Convolutional Neural Networks (CNNs) have been successfully applied to many computer vision tasks, such as image classification. By performing linear combinations and element-wise nonlinear operations, these networks can be thought of as extracting solely first-order information from an input image. In the past, however, second-order statistics computed from handcrafted features, e.g., covarian...

In this work, we demonstrate an integrated, single-layer, miniature flow cytometry device that is capable of multi-parametric particle analysis. The device integrates both particle focusing and detection components on-chip, including a "microfluidic drifting" based three-dimensional (3D) hydrodynamic focusing component and a series of optical fibers integrated into the microfluidic architecture...

We present a recurrent neural architecture with parametric bias for actively perceiving objects. A humanoid robot learns to extract sensorimotor laws and based on those to classify eight objects by exploring their multimodal sensory characteristics. The network is either trained with prototype sequences for all objects or just two objects. In both cases the network is able to self-organize the ...

We recently presented a new model for singing synthesis based on a modified version of the WaveNet architecture. Instead of modeling raw waveform, we model features produced by a parametric vocoder that separates the influence of pitch and timbre. This allows conveniently modifying pitch to match any target melody, facilitates training on more modest dataset sizes, and significantly reduces tra...

We present a new model for singing synthesis based on a modified version of the WaveNet architecture. Instead of modeling raw waveform, we model features produced by a parametric vocoder that separates the influence of pitch and timbre. This allows conveniently modifying pitch to match any target melody, facilitates training on more modest dataset sizes, and significantly reduces training and g...

Functional-structural models provide detailed representations of tree growth and their application to forestry seems full of prospects. However, due to the complexity of tree architecture, parametric identification of such models remains a critical issue. We present the GreenLab approach for modeling tree growth. It simulates tree plasticity in response to changes of their internal level of tro...

Real-time parametric statistical analysis of functional MRI (fMRI) data would potentially enlarge the scope of experimentation and facilitate its application to clinical populations. A system is described that addresses the need for rapid analysis of fMRI data and lays the foundation for dealing with problems that impede the application of fMRI to clinical populations. The system, I/OWA (Input/...