Boahen, Kwabena A

Email Address
ORCID
Disciplines
Research Projects
Organizational Units
Position
Introduction
Research Interests

Filters

2000 - 200725
25
1411
Reset filters

Settings

Search Results

Now showing 1 - 10 of 25
  • Publication
    A burst-mode word-serial address-event link--III: analysis and test results
    (2004-07-01) Boahen, Kwabena A
    We present results for a scalable multiple-access inter-chip link that communicates binary activity between two-dimensional arrays fabricated in deep submicrometer CMOS. Capacity scales with integration density because an entire row is read and written in parallel. Row activity is encoded in a burst: The row address followed by a column address for each active cell. We predict the distribution of burst lengths when transmission is initiated by active cells and access is arbitered using a two-level queuing model. Agreement with the experiment is excellent for loads over 50% but not for lighter loads, where our assumption that service time is exponentially distributed breaks down. We also quantify the throughput–latency tradeoff. The price of an n-fold increase in throughput is an n per Ncol timing error in a cell’s inter-event interval, where Ncol is the number of cells per row. Links implemented in 0.6, 0.4, and 0.25 micrometer are compared; the highest burst-rate achieved was 27.8 M events/s.
  • Publication
    A multi-chip implementation of cortical orientation hypercolumns
    (2004-05-23) Choi, Thomas Y. W.; Shi, Bertram E.; Boahen, Kwabena A
    This paper describes a neuromorphic implementation of the orientation hypercolumns found in the mammalian primary visual cortex. A hypercolumn contains a group of neurons that respond to the same retinal location, but with different orientation preferences. The system consists of a single silicon retina feeding multiple orientation selective chips, each of which contains neurons tuned to the same orientation, but with different receptive field centers and spatial phases. All chips operate in continuous time, and communicate with each other using spikes transmitted by the asynchronous digital Address Event Representation communication protocol. This enables us to implement recurrent interactions between neurons within one hypercolumn, even though they are located on different chips. We demonstrate this by measuring shifts in orientation selectivity due to changes in the feedback.
  • Publication
    A biomorphic digital image sensor
    (2003-02-01) Culurciello, Eugenio; Etienne-Cummings, Ralph; Boahen, Kwabena A
    An arbitrated address-event imager has been designed and fabricated in a 0.6-μm CMOS process. The imager is composed of 80 x 60 pixels of 32 x 30 μm. The value of the light intensity collected by each photosensitive element is inversely proportional to the pixel’s interspike time interval. The readout of each spike is initiated by the individual pixel; therefore, the available output bandwidth is allocated according to pixel output demand. This encoding of light intensities favors brighter pixels, equalizes the number of integrated photons across light intensity, and minimizes power consumption. Tests conducted on the imager showed a large output dynamic range of 180 dB (under bright local illumination) for an individual pixel. The array, on the other hand, produced a dynamic range of 120 dB (under uniform bright illumination and when no lower bound was placed on the update rate per pixel). The dynamic range is 48.9 dB value at 30-pixel updates/s. Power consumption is 3.4 mW in uniform indoor light and a mean event rate of 200 kHz, which updates each pixel 41.6 times per second. The imager is capable of updating each pixel 8.3K times per second (under bright local illumination).
  • Publication
    Contrast Adaptation in Subthreshold and Spiking Responses of Mammalian Y-Type Retinal Ganglion Cells
    (2005-01-26) Zaghloul, Kareem A; Boahen, Kwabena A; Demb, Jonathan B
    Retinal ganglion cells adapt their responses to the amplitude of fluctuations around the mean light level, or the "contrast." But, in mammalian retina, it is not known whether adaptation arises exclusively at the level of synaptic inputs or whether there is also adaptation in the process of ganglion cell spike generation. Here, we made intracellular recordings from guinea pig Y-type ganglion cells and quantified changes in contrast sensitivity (gain) using a linear-nonlinear analysis. This analysis allowed us to measure adaptation in the presence of nonlinearities, such as the spike threshold, and to compare adaptation in subthreshold and spiking responses. At high contrast (0.30), relative to low contrast (0.10), gain reduced to 0.82 ± 0.016 (mean ± SEM) for the subthreshold response and to 0.61 ± 0.011 for the spiking response. Thus, there was an apparent reduction in gain between the subthreshold and spiking response of 0.74 ± 0.013. Control experiments suggested that the above effects could not be explained by an artifact of the intracellular recording conditions: extracellular recordings showed a gain change of 0.58 ± 0.022. For intracellular recordings, negative current reduced the spike output but did not affect the gain change in the subthreshold response: 0.80 ± 0.051. Thus, adaptation in the subthreshold response did not require spike-dependent conductances. We conclude that the contrast-dependent gain change in the spiking response can be explained by both a synaptic mechanism, as reflected by responses in the subthreshold potential, and an intrinsic mechanism in the ganglion cell related to spike generation.
  • Publication
    Recurrently Connected Silicon Neurons with Active Dendrites for One-Shot Learning
    (2004-07-25) Arthur, John V.; Boahen, Kwabena A
    We describe a neuromorphic chip designed to model active dendrites, recurrent connectivity, and plastic synapses to support one-shot learning. Specifically, it is designed to capture neural firing patterns (short-term memory), memorize individual patterns (long-term memory), and retrive them when primed (associative recall). It consists of a recurrently connected population of excitatory pyramidal cells and a recurrently connected population of inhibitory basket cells. In addition to their recurrent connections, the excitatory and inhibitory populations are reciprocally connected. The model is novel in that it utilizes recurrent connections and active dendrites to maintain short-term memories as well as to store long-term memories.
  • Publication
    Self-organized cortical map formation by guiding connections
    (2005-05-23) Lam, Stanley Y.M.; Shi, Bertram E.; Boahen, Kwabena A
    We describe an algorithm for self-organizing connections from a source array to a target array of neurons that is inspired by neural growth cone guidance. Each source neuron projects a Gaussian pattern of connections to the target layer. Learning modifies the pattern center location. The small number of parameters required to specify connectivity has enabled this algorithm's implementation in a neuromorphic silicon system. We demonstrate that this algorithm can lead to topographic feature maps similar to those observed in the visual cortex, and characterize its operation as function maximization, which connects this approach with other models of cortical map formation.
  • Publication
    A burst-mode word-serial address-event link--II: receiver design
    (2004-07-01) Boahen, Kwabena A
    We present a receiver for a scalable multiple-access inter-chip link that communicates binary activity between two-dimensional arrays fabricated in deep submicron CMOS. Recipients are identified by row and column addresses but these addresses are not communicated simultaneously. The row address is followed sequentially by a column address for each active cell in that row; this cuts pad count in half without sacrificing communication capacity. Column addresses are decoded as they are received but cells are not written individually. An entire burst is written to a row in parallel; this increases communication capacity with integration density. Rows are written one by one but bursts are not processed one at a time. The next burst is decoded while the last one is being written; this increases capacity further. We synthesized an asynchronous implementation by performing a series of program decompositions, starting from a high-level description. Links using this design have been implemented successfully in three generations of submicron CMOS technology.
  • Publication
    A retinomorphic chip with parallel pathways : encoding INCREASING, ON, DECREASING, and OFF visual signals
    (2001-02-12) Boahen, Kwabena A
    Retinomorphic chips may improve their spike-coding efficiency by emulating the primate retina's parallel pathways. To model the four predominant ganglion-cell types in the cat retina, I morphed outer and inner retina microcircuits into a silicon chip, Visio1. It has 104 x 96 photoreceptors, 4 x 52 x 48 ganglion-cells, a die size of 9.25 x 9.67 mm2 in 1.2 µm 5V CMOS, and consumes 11.5 mW at 5 spikes/second/ganglion-cell. Visio1 includes novel subthreshold current-mode circuits that model horizontal-cell autofeedback, to decouple spatial filtering from local gain control, and model amacrine-cell loop-gain modulation, to adapt temporal filtering to motion. Different ganglion cells respond to motion in a quadrature sequence, making it possible to detect edges of one contrast or the other moving in one direction or the other. I present results from a multichip 2-D motion system, which implements Watson and Ahumada's model of human visual-motion sensing.
  • Publication
    A recurrent model of orientation maps with simple and complex cells
    (2003-12-09) Merolla, Paul; Boahen, Kwabena A
    We describe a neuromorphic chip that utilizes transistor heterogeneity, introduced by the fabrication process, to generate orientation maps similar to those imaged in vivo. Our model consists of a recurrent network of excitatory and inhibitory cells in parallel with a push-pull stage. Similar to a previous model the recurrent network displays hotspots of activity that give rise to visual feature maps. Unlike previous work, however, the map for orientation does not depend on the sign of contrast. Instead, sign-independent cells driven by both ON and OFF channels anchor the map, while push-pull interactions give rise to sign-preserving cells. These two groups of orientation-selective cells are similar to complex and simple cells observed in V1.
  • Publication
    An ON–OFF Log Domain Circuit That Recreates Adaptive Filtering in the Retina
    (2005-01-01) Zaghloul, Kareem A.; Boahen, Kwabena A
    We introduce a new approach to synthesizing Class AB log-domain filters that satisfy dynamic differential-mode and common-mode constraints simultaneously. Whereas the dynamic differential-mode constraint imposes the desired filtering behavior, the dynamic common-mode constraint solves the zero-dc-gain problem, a shortcoming of previous approaches. Also, we introduce a novel push–pull circuit that serves as a current-splitter; it rectifies a differential signal into the ON and OFF paths in our log-domain filter. As an example, we synthesize a first-order low-pass filter, and, to demonstrate the rejection of dc signals, we implement an adaptive filter by placing this low-pass circuit in a variable-gain negative-feedback path. Feedback gain is controlled by signal energy, which is extracted simply by summing complementary ON and OFF signals—dc signals do not contribute to the signal energy nor are they amplified by the feedback. We implement this adaptive filter design in a silicon chip that draws biological inspiration from visual processing in the mammalian retina. It may also be useful in other applications that require dynamic time-constant adaptation.