Fast sensory motor control based on event-based hybrid neuromorphic-procedural system

Delbrück, Tobi; Lichtsteiner, P.

doi:10.1109/iscas.2007.378038

Cited by 112 publications

(117 citation statements)

References 2 publications

Supporting

Mentioning

117

Contrasting

Order By: Relevance

“…Only positive (excitatory) spikes are generated by BSA, whereas all other techniques mentioned here can also generate negative (inhibitory) spikes. Temporal Contrast was originally implemented in hardware (Delbruck and Lichtsteiner, 2007) in the artificial silicon retina. It represents significant changes in signal intensity over a given threshold, where the ON and OFF events are dependent on the sign of the changes.…”

Section: Data Encodingmentioning

confidence: 99%

“…It is trained and tested in a hold out method. Firstly we converted the video data into discrete spike trains using the Temporal Contrast encoding method to discretize the continuous signal, following the example of the silicon retina (Delbruck and Lichtsteiner, 2007). The deSNN classified mentioned previously is used here as an output classifier, because deSNN is computationally efficient and emphasizes the importance of the first spike, which has been observed in biological vision systems.…”

Section: Estdm For Video Data Recognitionmentioning

confidence: 99%

“…Examples of problems involving SSTD are: brain cognitive state evaluation based on spatially distributed EEG electrodes (Kasabov, 2014); fMRI data (Mitchell et al, 2003;Chu et al, 2011;Gholami Doborjeh and Kasabov, 2015;Just, 2001;Murli et al, 2014); moving object recognition from video data (Delbruck and Lichtsteiner, 2007); evaluating risk of disease, e.g. heart attack, stroke ; evaluating response of a disease to treatment based on clinical and environmental variables; modelling the progression of a neuro-degenerative disease, such as Alzheimer's Disease; modelling and prognosis of the establishment of invasive species in ecology.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Evolving spatio-temporal data machines based on the NeuCube neuromorphic framework: Design methodology and selected applications

et al. 2016

View full text Add to dashboard Cite

The paper describes a new type of evolving connectionist systems (ECOS) called evolving spatio-temporal data machines based on neuromorphic, brain-like information processing principles (eSTDM). These are multi-modular computer systems designed to deal with large and fast spatio/spectro temporal data using spiking neural networks (SNN) as major processing modules. ECOS and eSTDM in particular can learn incrementally from data streams, can include 'on the fly' new input variables, new output class labels or regression outputs, can continuously adapt their structure and functionality, can be visualised and interpreted for new knowledge discovery and for a better understanding of the data and the processes that generated it. eSTDM can be used for early event prediction due to the ability of the SNN to spike early, before whole input vectors (they were trained on) are presented. A framework for building eSTDM called NeuCube along with a design methodology for building eSTDM using this are presented. The implementation of this framework in MATLAB, Java, and PyNN (Python) is presented. The latter facilitates the use of neuromorphic hardware platforms to run the eSTDM. Selected examples are given of eSTDM for pattern recognition and early event prediction on EEG data, fMRI data, multisensory seismic data, ecological data, climate data, audio-visual data. Future directions are discussed, including extension of the NeuCube framework for building neurogenetic eSTDM and also new applications of eSTDM.

show abstract

Section: Data Encodingmentioning

confidence: 99%

Section: Estdm For Video Data Recognitionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Evolving spatio-temporal data machines based on the NeuCube neuromorphic framework: Design methodology and selected applications

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Neuromorphic systems have been greatly developed and steadily redefined with the progress of the VLSI technology and the computational neuroscience over the past quarter century [1][2][3][4][5][6][7][8][9][10][11][12][13][14]. For the front-end of the intelligent and smart sensors, neuromorphic sensory systems based on silicon retina [1] and silicon cochlea [4] have been designed and fabricated.…”

Section: Introductionmentioning

confidence: 99%

“…For robot and biomedical applications, neuromorphic motor systems based on the central pattern generator have been implemented on various silicon platforms [6][7][8][9][10]. Such neuromorphic systems are integrated into fast sensory-motor processing systems [11,12]. More recently, cognitive neuromorphic systems exploiting spike-based computation have been progressed for achieving higher order brain functions including working memory, saliency detection, selective attention, and perceptual decision-making.…”

Section: Introductionmentioning

confidence: 99%

Dynamical systems design of silicon neurons using phase reduction method

Nakada

Miura

Asai

2016

NOLTA

View full text Add to dashboard Cite

Abstract:In biologically-inspired, neuromorphic engineering, it is important to design silicon neurons (SiNs) with desirable functions in a systematic way. However, the conventional design methods such as phenomenological design and the conductance-based design relied on the hand-tuned parameters. Thus a more systematic design principle, that considers mathematical structures in the dynamical systems, is needed for efficiency and robustness. In this work, we present the phase response curve (PRC)-based design for SiNs as a dynamical systems design for SiNs to enhance synchronization in an ensemble of SiNs on the basis of the phase reduction theory. By analyzing various circuit models of the previous SiNs, we explore key criteria to realize transitions between two typical PRCs, Type I and Type II. As a case study, we focus on the hybrid type SiNs for tractability and demonstrate how to tune circuit parameters of a resonate-and-fire neuron (RFN) circuit to control the peak location of phase coupling functions resulting from PRCs, which matters for phase locking.

show abstract