There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Loihi is a 60-mm2 chip fabricated in Intels 14-nm process that advances the state-of-the-art modeling of spiking neural networks in silicon. It integrates a wide range of novel features for the field, such as hierarchical connectivity, dendritic compartments, synaptic delays, and, most importantly, programmable synaptic learning rules. Running a spiking convolutional form of the Locally Competitive Algorithm, Loihi can solve LASSO optimization problems with over three orders of magnitude superior energy-delay-product compared to conventional solvers running on a CPU iso-process/voltage/area. This provides an unambiguous example of spike-based computation, outperforming all known conventional solutions.

Loihi: A Neuromorphic Manycore Processor with On-Chip Learning

Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the triplet network model, which aims to learn useful representations by distance comparisons. A similar model was defined by Wang et al. (2014), tailor made for learning a ranking for image information retrieval. Here we demonstrate using various datasets that our model learns a better representation than that of its immediate competitor, the Siamese network. We also discuss future possible usage as a framework for unsupervised learning.

Deep metric learning using Triplet network

One of the most important design problems for multi-UAV (Unmanned Air Vehicle) systems is the communication which is crucial for cooperation and collaboration between the UAVs. If all UAVs are directly connected to an infrastructure, such as a ground base or a satellite, the communication between UAVs can be realized through the in-frastructure. However, this infrastructure based communication architecture restricts the capabilities of the multi-UAV systems. Ad-hoc networking between UAVs can solve the problems arising from a fully infrastructure based UAV networks. In this paper, Flying Ad-Hoc Networks (FANETs) are surveyed which is an ad hoc network connecting the UAVs. The differences between FANETs, MANETs (Mobile Ad-hoc Networks) and VANETs (Vehicle Ad-Hoc Networks) are clarified first, and then the main FANET design challenges are introduced. Along with the existing FANET protocols, open research issues are also discussed.

Flying Ad-Hoc Networks (FANETs)

Guided by brain-like ‘spiking’ computational frameworks, neuromorphic computing—brain-inspired computing for machine intelligence—promises to realize artificial intelligence while reducing the energy requirements of computing platforms. This interdisciplinary field began with the implementation of silicon circuits for biological neural routines, but has evolved to encompass the hardware implementation of algorithms with spike-based encoding and event-driven representations. Here we provide an overview of the developments in neuromorphic computing for both algorithms and hardware and highlight the fundamentals of learning and hardware frameworks. We discuss the main challenges and the future prospects of neuromorphic computing, with emphasis on algorithm–hardware codesign. The authors review the advantages and future prospects of neuromorphic computing, a multidisciplinary engineering concept for energy-efficient artificial intelligence with brain-inspired functionality.

Towards spike-based machine intelligence with neuromorphic computing.

We consider the problem of localizing wireless nodes in an outdoor, open-space environment, using ad-hoc radio ranging measurements, e.g., 802.11. We cast these ranging measurements as a set of distance constraints, thus forming an over-determined system of equations suitable for non-linear least squares optimization. However, ranging measurements are often subject to errors, induced by multipath signals and variations in path loss, unreliable hardware or antenna connectors, or imperfection in measurement models. Such potentially large, non-Gaussian errors in the measurement data ultimately produce inaccurate localization solutions. We propose a new error-tolerant localization method, called snap-inducing shaped residuals (SISR), to identify automatically "bad nodes" and "bad links" arising from these errors, so that they receive less weight in the localization process. In particular, SISR snaps "good nodes" to their accurate locations and gives less emphasis to other nodes. While the mathematical techniques used by SISR are similar to robust statistics, SISR's exploitation of the snap-in effect in localization appears to be novel. We provide analysis on the principle of SISR, illustrate errors in real-world measurements, and demonstrate a working SISR implementation in field experiments on a testbed of 37 wireless nodes, as well as show the superior performance of SISR in simulation with a larger number of nodes.

/pdf/localization-with-snap-inducing-shaped-residuals-sisr-coping-23wwcm29w1.pdf

Localization with snap-inducing shaped residuals (SISR): coping with errors in measurement

Orthogonal matching pursuit (OMP) is an efficient approximation algorithm for computing sparse representations. However, prior research has shown that the representations computed by OMP may be of inferior quality, as they deliver suboptimal classification accuracy on several image datasets. We have found that this problem is caused by OMP's relatively weak stability under data variations, which leads to unreliability in supervised classifier training. We show that by imposing a simple nonnegativity constraint, this nonnegative variant of OMP (NOMP) can mitigate OMP's stability issue and is resistant to noise overfitting. In this work, we provide extensive analysis and experimental results to examine and validate the stability advantage of NOMP. In our experiments, we use a multi-layer deep architecture for representation learning, where we use K-means for feature learning and NOMP for representation encoding. The resulting learning framework is not only efficient and scalable to large feature dictionaries, but also is robust against input noise. This framework achieves the state-of-the-art accuracy on the STL-10 dataset.

Stable and Efficient Representation Learning with Nonnegativity Constraints

We are interested in estimating the angle of arrival of an RF signal by using commercial-off-the-shelf (COTS) software-defined radios (SDRs). The proposed COTS-based approach has the advantages of flexibility, low cost and ease of deployment, but-unlike traditional phased antenna arrays in which elements are already phase-aligned — we face the challenge of aligning individual SDRs during field deployment in order to ensure coherent phase detection. We propose a strategy to relax the requirement of tight phase synchronization between distributed oscillators by using a novel phase difference of arrival mechanism based on a field-deployable reference transmitter. This approach enables flexible and inexpensive COTS phased-array designs. We evaluate our method in an outdoor, 20m×20m open field and observe localization errors below 3m. We conclude that a COTS-based approach to RF source localization is amenable to rapid and low-cost deployment of sensing infrastructure and could potentially be of interest to the Intelligence, Surveillance and Reconnaissance (ISR) community at the tactical edge.

/pdf/determining-rf-angle-of-arrival-using-cots-antenna-arrays-a-33e7j0oesb.pdf

Determining RF angle of arrival using COTS antenna arrays: A field evaluation

We consider the problem of mitigating a highly varying wireless channel between a transmitting ground node and receivers on a small, low-altitude unmanned aerial vehicle (UAV) in a 802.11 wireless mesh network. One approach is to use multiple transmitter and receiver nodes that exploit the channel's spatial/temporal diversity and that cooperate to improve overall packet reception. We present a series of measurement results from a real-world testbed that characterize the resulting wireless channel. We show that the correlation between receiver nodes on the airplane is poor at small time scales so receiver diversity can be exploited. Our measurements suggest that using several receiver nodes simultaneously can boost packet delivery rates substantially. Lastly, we show that similar results apply to transmitter selection diversity as well.

/pdf/measuring-diversity-on-a-low-altitude-uav-in-a-ground-to-air-1fmi13hmeu.pdf

Tsung-Han Lin

Papers

Loihi: A Neuromorphic Manycore Processor with On-Chip Learning

Localization with snap-inducing shaped residuals (SISR): coping with errors in measurement

Stable and Efficient Representation Learning with Nonnegativity Constraints

Determining RF angle of arrival using COTS antenna arrays: A field evaluation

Measuring diversity on a low-altitude UAV in a ground-to-air wireless 802.11 mesh network