Learning long-term dependencies in NARX recurrent neural networks

It has previously been shown that gradient-descent learning algorithms for recurrent neural networks can perform poorly on tasks that involve long-term dependencies, i.e. those problems for which the desired output depends on inputs presented at times far in the past. We show that the long-term dependencies problem is lessened for a class of architectures called nonlinear autoregressive models with exogenous (NARX) recurrent neural networks, which have powerful representational capabilities. We have previously reported that gradient descent learning can be more effective in NARX networks than in recurrent neural network architectures that have "hidden states" on problems including grammatical inference and nonlinear system identification. Typically, the network converges much faster and generalizes better than other networks. The results in this paper are consistent with this phenomenon. We present some experimental results which show that NARX networks can often retain information for two to three times as long as conventional recurrent neural networks. We show that although NARX networks do not circumvent the problem of long-term dependencies, they can greatly improve performance on long-term dependency problems. We also describe in detail some of the assumptions regarding what it means to latch information robustly and suggest possible ways to loosen these assumptions.     

Designing power and performance optimal application-specific Network-on-Chip architectures

This paper presents an optimal method for topology synthesis by taking into account factors related to power, performance, and contention in an application-specific Network-on-Chip (NoC) architecture. A Tabu search based approach is used for topology generation with an automated design technique, incorporating floorplan information to attain accurate values for power consumption of the routers and physical links. The Tabu search method incorporates multiple objectives and is able to generate optimal NoC topologies which account for both power and performance. The contention analysis technique assesses performance and relieves any potential bottlenecks using virtual channel insertion after considering its effect on power consumption and performance improvement within the NoC. The contention analyzer uses a Layered Queuing Network approach to model the rendezvous interactions among system components. Several experiments are conducted using various SoC benchmark applications to compare the power and performance outcomes of the proposed technique.     

Extracting finite-state representations from recurrent neuralnetworks trained on chaotic symbolic sequences

Concerns neural-based modeling of symbolic chaotic time series. We investigate the knowledge induction process associated with training recurrent mural nets (RNN) on single long chaotic symbolic sequences. Even though training RNN to predict the next symbol leaves the standard performance measures such as the mean square error on the network output virtually unchanged, the nets extract a lot of knowledge. We monitor the knowledge extraction process by considering the nets stochastic sources and letting them generate sequences which are then confronted with the training sequence via information theoretic entropy and cross-entropy measures. We also study the possibility of reformulating the knowledge gained by RNN in a compact easy-to-analyze form of finite-state stochastic machines. The experiments are performed on two sequences with different complexities measured by the size and state transition structure of the induced Crutchfield's epsilon-machines (1991, 1994). The extracted machines can achieve comparable or even better entropy and cross-entropy performance. They reflect the training sequence complexity in their dynamical state representations that can be reformulated using finite-state means. The findings are confirmed by a much more detailed analysis of model generated sequences. We also introduce a visual representation of allowed block structure in the studied sequences that allows for an illustrative insight into both RNN training and finite-state stochastic machine extraction processes.     

Spatial representation of symbolic sequences through iterativefunction systems

Jeffrey proposed (1990) a graphic representation of DNA sequences using Barnsley's iterative function systems. In spite of further developments in this direction, the proposed graphic representation of DNA sequences has been lacking a rigorous connection between its spatial scaling characteristics and the statistical characteristics of the DNA sequences themselves. We 1) generalize Jeffrey's graphic representation to accommodate (possibly infinite) sequences over an arbitrary finite number of symbols; 2) establish a direct correspondence between the statistical characterization of symbolic sequences via Renyi entropy spectra (1959) and the multifractal characteristics (Renyi generalized dimensions) of the sequences' spatial representations; 3) show that for general symbolic dynamical systems, the multifractal f_H-spectra in the sequence space coincide with the f_H -spectra on spatial sequence representations     

Weibull Analysis of Electrical Breakdown Strength as an Effective Means of Evaluating Elastomer Thin Film Quality

To realize the commercial potential of dielectric elastomers, reliable, large‐scale film production is required. Ensuring proper mixing and subsequently avoiding demixing after, for example, pumping and coating of elastomer premix in an online process is not facile. Weibull analysis of the electrical breakdown strength of dielectric elastomer films is shown to be an effective means of evaluating the film quality. The analysis is shown to be capable of distinguishing between proper and improper mixing schemes where similar analysis of ultimate mechanical properties fails to distinguish.

     

Non-contrast myocardial perfusion in rest and exercise stress using systolic flow-sensitive alternating inversion recovery

Objective

To evaluate systolic flow-sensitive alternating inversion recovery (FAIR) during rest and exercise stress using 2RR (two cardiac cycles) or 1RR intervals between inversion pulse and imaging.

Materials and methods

1RR and 2RR FAIR was implemented on a 3T scanner. Ten healthy subjects were scanned during rest and stress. Stress was performed using an in-bore ergometer. Heart rate, mean myocardial blood flow (MBF) and temporal signal-to-noise ratio (TSNR) were compared using paired t tests.

Results

Mean heart rate during stress was higher than rest for 1RR FAIR (85.8 ± 13.7 bpm vs 63.3 ± 11.1 bpm; p < 0.01) and 2RR FAIR (83.8 ± 14.2 bpm vs 63.1 ± 10.6 bpm; p < 0.01). Mean stress MBF was higher than rest for 1RR FAIR (2.97 ± 0.76 ml/g/min vs 1.43 ± 0.6 ml/g/min; p < 0.01) and 2RR FAIR (2.8 ± 0.96 ml/g/min vs 1.22 ± 0.59 ml/g/min; p < 0.01). Resting mean MBF was higher for 1RR FAIR than 2RR FAIR (p < 0.05), but not during stress. TSNR was lower for stress compared to rest for 1RR FAIR (4.52 ± 2.54 vs 10.12 ± 3.69; p < 0.01) and 2RR FAIR (7.36 ± 3.78 vs 12.41 ± 5.12; p < 0.01). 2RR FAIR TSNR was higher than 1RR FAIR for rest (p < 0.05) and stress (p < 0.001).

Discussion

We have demonstrated feasibility of systolic FAIR in rest and exercise stress. 2RR delay systolic FAIR enables non-contrast perfusion assessment during stress with relatively high TSNR.

     

Generalized far-infrared magneto-optic ellipsometry for semiconductor layer structures: determination of free-carrier effective-mass,mobility, and concentration parameters in n-type GaAs

We report for the first time on the application of generalized ellipsometry at far-infrared wavelengths (wave numbers from 150 cm(-1) to 600 cm(-1)) for measurement of the anisotropic dielectric response of doped polar semiconductors in layered structures within an external magnetic field. Upon determination of normalized Mueller matrix elements and subsequent derivation of the normalized complex Jones reflection matrix r of an n-type doped GaAs substrate covered by a highly resistive GaAs layer, the spectral dependence of the room-temperature magneto-optic dielectric function tensor of n-type GaAs with free-electron concentration of 1.6 x 10(18) cm(-3) at the magnetic field strength of 2.3 T is obtained on a wavelength-by-wavelength basis. These data are in excellent agreement with values predicted by the Drude model. From the magneto-optic generalized ellipsometry measurements of the layered structure, the free-carrier concentration, their optical mobility, the effective-mass parameters, and the sign of the charge carriers can be determined independently, which will be demonstrated. We propose magneto-optic generalized ellipsometry as a novel approach for exploration of free-carrier parameters in complex organic or inorganic semiconducting material heterostructures, regardless of the anisotropic properties of the individual constituents.     

Rod-shaped nanocrystals elicit neuronal activity in vivo

The development of novel nanomaterials has raised great interest in efforts to evaluate their effect on biological systems, ranging from single cells to whole animals. In particular, there exists an open question regarding whether nanoparticles per se can elicit biological responses, which could interfere with the phenomena they are intended to measure. Here it is reported that challenging the small cnidaria Hydra vulgaris in vivo with rod-shaped semiconductor nanoparticles, also known as quantum rods (QRs), results in an unexpected tentacle-writhing behavior, which is Ca(2+) dependent and relies on the presence of tentacle neurons. Due to the absence of surface functionalization of the QRs with specific ligands, and considering that spherical nanoparticles with same composition as the QRs fail to induce any in vivo behavior on the same experimental model, it is suggested that unique shape-tunable electrical properties of the QRs may account for the neuronal stimulation. This model system may represent a widely applicable tool for screening neuronal response to nanoparticles in vivo.