Representation of functional data in neural networks

Representation of functional data in neural networks

Functional Data Analysis (FDA) is an extension of traditional data analysis to functional data, for example spectra, temporal series, spatio-temporal images, gesture recognition data, etc. Functional data are rarely known in practice; usually a regular or irregular sampling is known. For this reason, some processing is needed in order to benefit from the smooth character of functional data in t...

Convolutional Neural Networks using Logarithmic Data Representation

Recent advances in convolutional neural networks have considered model complexity and hardware efficiency to enable deployment onto embedded systems and mobile devices. For example, it is now well-known that the arithmetic operations of deep networks can be encoded down to 8-bit fixed-point without significant deterioration in performance. However, further reduction in precision down to as low ...

Knowledge Representation in Neural Networks

Recall the earlier definition of intelligence as doing the right thing at the right time, as judged by an outside human observer. As a key facilitator of intelligence, knowledge can then be defined as background information or general understanding (of a variety of domains) that enhances the ability to act intelligently, where domains include the natural, social, and even virtual worlds, as wel...

Representation of Adsorption Data for the Case of Energetically Heterogeneous Solid Surfaces Using Artificial Neural Network

Symbolic Representation of Neural Networks

Although backpropagation neural networks generally predict better than decision trees do for pattern classiication problems, they are often regarded as black boxes, i.e., their predictions cannot be explained as those of decision trees. In many applications, more often than not, explicit knowledge is needed by human experts. This work drives a symbolic representation for neural networks to make...