Echo State Networks (ESN) are a class of Recurrent Neural Networks (RNN) that has gained substantial popularity due to their effectiveness, ease of use and potential for compact hardware implementation. An ESN contains the three network layers input, reservoir and readout where the reservoir is the truly recurrent network. The input and reservoir layers of an ESN are initialized at random and never trained afterwards and the training of the ESN is applied to the readout layer only. The alternative of Recursive Neural Gas (RNG) is one of the many proposals of fully-trainable reservoirs that can be found in the literature. Although some improvements in performance have been reported with RNG, to the best of authors' knowledge, no experimental comparative results are known with benchmarks for which ESN is known to yield excellent results. This work describes an accurate model of RNG together with some extensions to the models presented in the literature and shows comparative results on three well-known and accepted datasets. The experimental results obtained show that, under specific circumstances, RNG-based reservoirs can achieve better performance.
Deep Convolutional Neural Networks (DCNNs) achieve state of the art results compared to classic machine learning in many applications that need recognition, identification and classification. An ever-increasing embedded deployment of DCNNs inference engines thus supporting the intelligence close to the sensor paradigm has been observed, overcoming limitations of cloud-based computing as bandwidth requirements, security, privacy, scalability, and responsiveness. However, increasing the robustness and accuracy of DCNNs comes at the price of increased computational cost. As result, implementing CNNs on embedded devices with real-time constraints is a challenge if the lowest power consumption shall be achieved. A solution to the challenge is to take advantage of the intra-device massive fine grain parallelism offered by these systems and benefit from the extensive concurrency exhibited by DCNN processing pipelines. The trick is to divide intensive tasks into smaller, weakly interacting batches subject to parallel processing. Referred to that, this paper has mainly two goals: 1) describe the implementation of a state-of-art technique to map DCNN most intensive tasks (dominated by multiply-and-accumulate ops) onto Orlando SoC, an ultra-low power heterogeneous multi cores developed by STMicroelectronics; 2) integrate the proposed implementation on a toolchain that allows deep learning developers to deploy DCNNs on low-power applications.
Hyperspectral images collected by remote sensing have played a significant role in the discovery of aqueous alteration minerals, which in turn have important implications for our understanding of the changing habitability on Mars. Traditional spectral analyzes based on summary parameters have been helpful in converting hyperspectral cubes into readily visualizable three channel maps highlighting high-level mineral composition of the Martian terrain. These maps have been used as a starting point in the search for specific mineral phases in images. Although the amount of labor needed to verify the presence of a mineral phase in an image is quite limited for phases that emerge with high abundance, manual processing becomes laborious when the task involves determining the spatial extent of detected phases or identifying small outcrops of secondary phases that appear in only a few pixels within an image. Thanks to extensive use of remote sensing data and rover expeditions, significant domain knowledge has accumulated over the years about mineral composition of several regions of interest on Mars, which allow us to collect reliable labeled data required to train machine learning algorithms. In this study we demonstrate the utility of machine learning in two essential tasks for hyperspectral data analysis: nonlinear noise removal and mineral classification. We develop a simple yet effective hierarchical Bayesian model for estimating distributions of spectral patterns and extensively validate this model for mineral classification on several test images. Our results demonstrate that machine learning can be highly effective in exposing tiny outcrops of specific phases in orbital data that are not uncovered by traditional spectral analysis. We package implemented scripts, documentation illustrating use cases, and pixel-scale training data collected from dozens of well-characterized images into a new toolkit. We hope that this new toolkit will provide advanced and effective processing tools and improve community's ability to map compositional units in remote sensing data quickly, accurately, and at scale.
In an era of complex networked parallel heterogeneous systems, simulating independently only parts, components, or attributes of a system-under-design is a cumbersome, inaccurate, and inefficient approach. Moreover, by considering each part of a system in an isolated manner, and due to the numerous and highly complicated interactions between the different components, the system optimization capabilities are severely limited. The presented fully-distributed simulation framework (called as COSSIM) is the first known open-source, high-performance simulator that can handle holistically system-of-systems including processors, peripherals and networks; such an approach is very appealing to both Cyber Physical Systems (CPS) and Highly Parallel Heterogeneous Systems designers and application developers. Our highly integrated approach is further augmented with accurate power estimation and security sub-tools that can tap on all system components and perform security and robustness analysis of the overall system under design—something that was unfeasible up to now. Additionally, a sophisticated Eclipse-based Graphical User Interface (GUI) has been developed to provide easy simulation setup, execution, and visualization of results. COSSIM has been evaluated when executing the widely used Netperf benchmark suite as well as a number of real-world applications. Final results demonstrate that the presented approach has up to 99% accuracy (when compared with the performance of the real system), while the overall simulation time can be accelerated almost linearly with the number of CPUs utilized by the simulator.
In this paper, for the first time the design of a HW module to eliminate the effect of the gravity acceleration from data acquired from inertial sensors is presented. A new "hardware friendly" algorithm has been derived from the Rodrigues' rotation formula, which can be implemented in a more compact iterative structure. By exploiting 32-bit floating-point arithmetic, the design is able to combine high accuracy and low power requirements needed by any intelligent Human Activity Recognition system, based on artificial neural networks. Synthesis with 65 nm CMOS std _cells returns a power dissipation below 2 μ W and an area of about 0.05 mm 2 , Results are the current state-of-the-art for this kind of system and they are very promising for the future integration in smart sensors for wearable applications.
Hundreds of millions of images are uploaded to the cloud every day. Innovative applications able to analyze and extract efficiently information from such a big database are needed nowadays more than ever. Visual Search is an application able to retrieve information of a query image comparing it against a large image database. In this paper a Visual Search pipeline implementation is presented able to retrieve multiple objects depicted in a single query image. Quantitative and qualitative precision results are shown on both real and synthetic datasets.
In this demo, we present COSSIM, an open-source simulation framework for cloud applications. Our solution models the client and server computing devices as well as the network that comprise the overall system and thus provides cycle accurate results, realistic communications and power/energy consumption estimates based on the actual dynamic usage scenarios. The simulator provides the necessary hooks to security testing software and can be extended through an IEEE standardized interface to include additional tools, such as simulators of physical models. The application that will be used to demonstrate COSSIM is mobile visual search, where mobile nodes capture images, extract their compressed representation and dispatch a query to the cloud. A server compares the received query to a local database and sends back some of the corresponding results.
