As convolutional neural networks (CNNs) enable state-of-the-art computer vision applications, their high energy consumption has emerged as a key impediment to their deployment on embedded and mobile ...devices. Towards efficient image classification under hardware constraints, prior work has proposed adaptive CNNs, i.e., systems of networks with different accuracy and computation characteristics, where a selection scheme adaptively selects the network to be evaluated for each input image. While previous efforts have investigated different network selection schemes, we find that they do not necessarily result in energy savings when deployed on mobile systems. The key limitation of existing methods is that they learn only how data should be processed among the CNNs and not the network architectures, with each network being treated as a blackbox. To address this limitation, we pursue a more powerful design paradigm where the architecture settings of the CNNs are treated as hyper-parameters to be globally optimized. We cast the design of adaptive CNNs as a hyper-parameter optimization problem with respect to energy, accuracy, and communication constraints imposed by the mobile device. To efficiently solve this problem, we adapt Bayesian optimization to the properties of the design space, reaching near-optimal configurations in few tens of function evaluations. Our method reduces the energy consumed for image classification on a mobile device by up to 6x, compared to the best previously published work that uses CNNs as blackboxes. Finally, we evaluate two image classification practices, i.e., classifying all images locally versus over the cloud under energy and communication constraints.
This paper presents a bistatic focusing solution for bistatic forward-looking SAR (BFL-SAR) in translational invariant case. The approach is based on the spectrum which is derived by time domain ...equivalency. According to strong range cell migration (RCM) of BFL-SAR, high order phase terms compensation is added to the algorithm. Simulation results show that the extended SIFFT algorithm can focus the BFL-SAR signal.
Scaled conjugate gradient (SCG) algorithm was used to improve adaptive neuro-fuzzy inference system (ANFIS). It’s proved by applications in chaotic time-series prediction that the improved ANFIS ...converges with less time and fewer iterations than standard ANFIS or ANFIS improved with the Fletcher-Reeves update method. The way in which ANFIS could be improved on the basis of standard algorithm using fuzzy logic toolbox of MATLAB is dwelled on. A convenient method to realize ANFIS in TI ’s digital signal processor (DSP) TMS320C5509 is presented. Results of experiments indicate that output of ANFIS realized in DSP coincides with that in MATLAB and validate this method.