Workshop Accomplishments

The workshop is the longest-funded NSF workshop, with 25 years of continuous support. The workshop has resulted in many new collaborations and scientific publications from participants, and has trained over 1000 participants. See this unfiltered list of recent google scholar citations mentioning "Telluride Neuromorphic". A few of the articles, papers and books resulting from workshop collaborations are highlighted below, see also Videos from past workshops to see a few examples of real time robot demonstrations.

Former workshop participants have founded startups (e.g. Intan Technologies, (intel) Nervana, Pixium Vision, inilabs, inivation, Chronocam, insightness, TeraDeep), have taken leadership positions at large industry (Amazon, Google, Intel, Comcast, Qualcomm), or are now professors at leading Universities (e.g. Yale, Purdue, Stanford, UCSD).

Past workshop participants have 2 out of the top 10 cited papers over the last decade at the IEEE Journal of Solid State Circuits. The cross-disciplinary nature of the workshop is shown by participants technical program organization at major scientific/technology conferences spanning electronics, computer vision, AI, robotics, and neuroscience, including ISSCC, ISCAS, BioCAS, CVPR, NIPS, SFN, and ARVO. Workshop organizers and participants have over 200,000 scientific citations.

Articles and publications from workshop collaborations

Scientific American article by Telluride collaborators

How Nerve Cells CommunicateThe brain makes sense of our experiences by focusing closely on the timing of the impulses that flow through billions of nerve cells

IEEE Spectrum article by Telluride Collaborators

How Neuromorphic Image Sensors Steal Tricks From the Human EyeBy prioritizing the dynamic parts of a scene, machines can capture images more efficiently

Books from Telluride collaborators

How to Build a Brain

Quick-Thinking AI Camera Mimics the Human BrainThe device will use artificial neurons and synapses to improve self-driving vehicle and drone performance 

The Journal Frontiers in Neuromorphic Engineering

Neuromorphic EngineeringNeuromorphic systems carry out robust and efficient neural computation using hardware implementations that operate in physical time. Typically they are event- or data-driven, they employ low-power, massively parallel hybrid analog/digital VLSI circuits, and they operate using the same physics of computation used by the nervous system. Although there are several forums for presenting research achievements in neuromorphic engineering, none are exclusively dedicated to this increasingly large research community. Either because they are dedicated to single disciplines, such as electrical engineering or computer science, or because they serve research communities which focus on analogous areas (such as biomedical engineering or computational neuroscience), but with fundamentally different goals and objectives. The mission of Neuromorphic Engineering is to provide a publication medium dedicated exclusively and specifically to this field. Topics covered by this publication include:  Analog and hybrid analog/digital electronic circuits for implementing neural processes, such as conductances, neurons, synapses, plasticity mechanisms, photoreceptors, cochleae, etc.  Neuromorphic circuits and systems for implementing real-time event-based neural processing architectures.  Hardware models of neural and sensorimotor processing systems, such as selective attention systems, coordinate transformation systems, auditory and/or visual processing systems, sensory fusion systems, etc.  Implementations of neural computational systems found in insects, birds, mammals, etc.  Embedded neuromorphic systems, including actuated or robotic platforms which process sensory signals and interact with the environment using event-based sensors and circuits. To ensure high quality and state-of-the-art material, publications should demonstrate experimental results, using physical implementations of neuromorphic systems, and possibly show the links between the artificial system and the neural/biological one they model.

Telluride collaboration on combining EEG and audio signal processing

Decoding the auditory brain with canonical component analysisThe relation between a stimulus and the brain response that it evokes can shed light on perceptual processes within the brain. It can also be harnessed to control external devices for Brain Computer Interface (BCI) applications. While the classic event-related potential (ERP) is appropriate for isolated stimuli, more sophisticated "decoding" strategies are needed to address ongoing stimuli such as speech, music or environmental sounds. Here we describe an approach based on Canonical Correlation Analysis (CCA) that finds the optimal transform to apply to both stimulus and response to reveal correlations between the two. Compared to prior methods based on forward or backward models for stimulus-response mapping, CCA finds significantly higher correlation scores, thus providing increased sensitivity to relatively small effects, and supports classifier schemes that yield higher classification scores. CCA strips the brain response of variance unrelated to the stimulus, and the stimulus representation of variance that does not affect the response, and thus improves our observation of the relation between stimulus and response.

Review articles from collaborators

Neuromorphic Silicon Neuron CircuitsHardware implementations of spiking neurons can be extremely useful for a large variety of applications, ranging from high-speed modeling of large-scale neural systems to real-time behaving systems, to bidirectional brain-machine interfaces. The specific circuit solutions used to implement silicon neurons depend on the application requirements. In this paper we describe the most common building blocks and techniques used to implement these circuits, and present an overview of a wide range of neuromorphic silicon neurons, which implement different computational models, ranging from biophysically realistic and conductance based Hodgkin-Huxley models to bi-dimensional generalized adaptive Integrate and Fire models. We compare the different design methodologies used for each silicon neuron design described, and demonstrate their features with experimental results, measured from a wide range of fabricated VLSI chips.

Page updated

Google Sites

Report abuse