https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

Simultaneous localization and mapping (SLAM) consists in the concurrent construction of a model of the environment (the map ), and the estimation of the state of the robot moving within it. The SLAM community has made astonishing progress over the last 30 years, enabling large-scale real-world applications and witnessing a steady transition of this technology to industry. We survey the current state of SLAM and consider future directions. We start by presenting what is now the de-facto standard formulation for SLAM. We then review related work, covering a broad set of topics including robustness and scalability in long-term mapping, metric and semantic representations for mapping, theoretical performance guarantees, active SLAM and exploration, and other new frontiers. This paper simultaneously serves as a position paper and tutorial to those who are users of SLAM. By looking at the published research with a critical eye, we delineate open challenges and new research issues, that still deserve careful scientific investigation. The paper also contains the authors’ take on two questions that often animate discussions during robotics conferences: Do robots need SLAM? and Is SLAM solved?

/pdf/past-present-and-future-of-simultaneous-localization-and-27i1pn9khc.pdf

Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age

Simultaneous Localization and Mapping (SLAM)consists in the concurrent construction of a model of the environment (the map), and the estimation of the state of the robot moving within it. The SLAM community has made astonishing progress over the last 30 years, enabling large-scale real-world applications, and witnessing a steady transition of this technology to industry. We survey the current state of SLAM. We start by presenting what is now the de-facto standard formulation for SLAM. We then review related work, covering a broad set of topics including robustness and scalability in long-term mapping, metric and semantic representations for mapping, theoretical performance guarantees, active SLAM and exploration, and other new frontiers. This paper simultaneously serves as a position paper and tutorial to those who are users of SLAM. By looking at the published research with a critical eye, we delineate open challenges and new research issues, that still deserve careful scientific investigation. The paper also contains the authors' take on two questions that often animate discussions during robotics conferences: Do robots need SLAM? and Is SLAM solved?

/pdf/past-present-and-future-of-simultaneous-localization-and-dhljw0akg5.pdf

Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age

This paper describes a 128 times 128 pixel CMOS vision sensor. Each pixel independently and in continuous time quantizes local relative intensity changes to generate spike events. These events appear at the output of the sensor as an asynchronous stream of digital pixel addresses. These address-events signify scene reflectance change and have sub-millisecond timing precision. The output data rate depends on the dynamic content of the scene and is typically orders of magnitude lower than those of conventional frame-based imagers. By combining an active continuous-time front-end logarithmic photoreceptor with a self-timed switched-capacitor differencing circuit, the sensor achieves an array mismatch of 2.1% in relative intensity event threshold and a pixel bandwidth of 3 kHz under 1 klux scene illumination. Dynamic range is > 120 dB and chip power consumption is 23 mW. Event latency shows weak light dependency with a minimum of 15 mus at > 1 klux pixel illumination. The sensor is built in a 0.35 mum 4M2P process. It has 40times40 mum2 pixels with 9.4% fill factor. By providing high pixel bandwidth, wide dynamic range, and precisely timed sparse digital output, this silicon retina provides an attractive combination of characteristics for low-latency dynamic vision under uncontrolled illumination with low post-processing requirements.

/pdf/a-128-times-128-120-db-15-mu-s-latency-asynchronous-temporal-3bv4hgi11i.pdf

A 128 $\times$ 128 120 dB 15 $\mu$ s Latency Asynchronous Temporal Contrast Vision Sensor

Event-based dynamic vision sensors (DVSs) asynchronously report log intensity changes. Their high dynamic range, sub-ms latency and sparse output make them useful in applications such as robotics and real-time tracking. However they discard absolute intensity information which is useful for object recognition and classification. This paper presents a dynamic and active pixel vision sensor (DAVIS) which addresses this deficiency by outputting asynchronous DVS events and synchronous global shutter frames concurrently. The active pixel sensor (APS) circuits and the DVS circuits within a pixel share a single photodiode. Measurements from a 240×180 sensor array of 18.5 μm 2 pixels fabricated in a 0.18 μm 6M1P CMOS image sensor (CIS) technology show a dynamic range of 130 dB with 11% contrast detection threshold, minimum 3 μs latency, and 3.5% contrast matching for the DVS pathway; and a 51 dB dynamic range with 0.5% FPN for the APS readout.

A 240 × 180 130 dB 3 µs Latency Global Shutter Spatiotemporal Vision Sensor

From the Publisher:
Neuromorphic engineers work to improve the performance of artificial systems through the development of chips and systems that process information collectively using primarily analog circuits. This book presents the central concepts required for the creative and successful design of analog VLSI circuits. The discussion is weighted toward novel circuits that emulate natural signal processing. Unlike most circuits in commercial or industrial applications, these circuits operate mainly in the subthreshold or weak inversion region. Moreover, their functionality is not limited to linear operations, but also encompasses many interesting nonlinear operations similar to those occurring in natural systems. Topics include device physics, linear and nonlinear circuit forms, translinear circuits, photodetectors, floating-gate devices, noise analysis, and process technology.

Analog VLSI: Circuits and Principles

Conventional image sensors produce massive amounts of redundant data and are limited in temporal resolution by the frame rate This paper reviews our recent breakthrough in the development of a high- performance spike-event based dynamic vision sensor (DVS) that discards the frame concept entirely, and then describes novel digital methods for efficient low-level filtering and feature extraction and high-level object tracking that are based on the DVS spike events These methods filter events, label them, or use them for object tracking Filtering reduces the number of events but improves the ratio of informative events Labeling attaches additional interpretation to the events, eg orientation or local optical flow Tracking uses the events to track moving objects Processing occurs on an event-by-event basis and uses the event time and identity as the basis for computation A common memory object for filtering and labeling is a spatial map of most recent past event times Processing methods typically use these past event times together with the present event in integer branching logic to filter, label, or synthesize new events These methods are straightforwardly computed on serial digital hardware, resulting in a new event- and timing-based approach for visual computation that efficiently integrates a neural style of computation with digital hardware All code is open- sourced in the jAER project (jaerwikisourceforgenet)

http://www.ini.ethz.ch/~tobi/wiki/lib/exe/fetch.php?id=publications&cache=cache&media=delbruckeventbasedvision_gcoe_symp_2008.pdf

Frame-free dynamic digital vision

The growing interest in pulse-mode processing by neural networks is encouraging the development of hardware implementations of massively parallel networks of integrate-and-fire neurons distributed over multiple chips. Address-event representation (AER) has long been considered a convenient transmission protocol for spike based neuromorphic devices. One missing, long-needed feature of AER-based systems is the ability to acquire data from complex neuromorphic systems and to stimulate them using suitable data. We have implemented a general-purpose solution in the form of a peripheral component interconnect (PCI) board (the PCI-AER board) supported by software. We describe the main characteristics of the PCI-AER board, and of the related supporting software. To show the functionality of the PCI-AER infrastructure we demonstrate a reconfigurable multichip neuromorphic system for feature selectivity which models orientation tuning properties of cortical neurons

/pdf/a-multichip-pulse-based-neuromorphic-infrastructure-and-its-2xsnngfc8x.pdf

Tobias Delbrück

Papers

A 128 $\times$ 128 120 dB 15 $\mu$ s Latency Asynchronous Temporal Contrast Vision Sensor

A 240 × 180 130 dB 3 µs Latency Global Shutter Spatiotemporal Vision Sensor

Analog VLSI: Circuits and Principles

Frame-free dynamic digital vision

A Multichip Pulse-Based Neuromorphic Infrastructure and Its Application to a Model of Orientation Selectivity