Abstract: A method of performing unsupervised detection of repeating patterns in a series (TS) of events (E21, E12, E5, . . . ), comprising the steps of: a) Providing a plurality of neurons (NR1-NRP), each neuron being representative of W event types; b) Acquiring an input packet (IV) comprising N successive events of the series; c) Attributing to at least some neurons a potential value (PT1-PTP), representative of the number of common events between the input packet and the neuron; d) Modifying the event types of neurons having a potential value exceeding a first threshold TL; and e) Generating a first output signal (OS1-OSP) for all neurons having a potential value exceeding a second threshold TF, and a second output signal, different from the first one, for all other neurons. A digital electronic circuit and system configured for carrying out the above method.

Abstract: A neuron circuit performing synapse learning on weight values includes a first sub-circuit, a second sub-circuit, and a third sub-circuit. The first sub-circuit is configured to receive an input signal from a pre-synaptic neuron circuit and determine whether the received input signal is an active signal having an active synapse value. The second sub-circuit is configured to compare a first cumulative reception counter of active input signals with a learning threshold value based on results of the determination. The third sub-circuit is configured to perform a potentiating learning process based on a first probability value to set a synaptic weight value of at least one previously received input signal to an active value, upon the first cumulative reception counter reaching the learning threshold value, and perform a depressing learning process based on a second probability value to set each of the synaptic weight values to an inactive value.

Abstract: This invention relates to a pixel circuit comprising a photo-sensor stage (10) comprising a photodiode (1) delivering a photoreceptor current (Iph), a comparison stage (30) configured for detecting a change in a signal voltage (Vph) derived from said photoreceptor current, a sample-and-hold circuit (50) connected to the converting stage (20) and to the comparison stage (30), said comparison stage (30) configured to output an input signal for the sample-and-hold circuit (50), and for emitting a sampling signal to a control terminal of the sample-and-hold circuit (50) when a change is detected in the signal voltage (Vph).

Abstract: A pixel circuit for detecting time-dependent visual data includes a photo sensing device detecting a light intensity and generating a signal representing the detected light intensity. The pixel circuit further includes: a voltage amplifier configured for amplifying the signal representing the detected light intensity and generating an amplified signal, the amplified signal being generated by taking into account a control signal which shifts an input voltage offset of the voltage amplifier; a hysteresis comparing module configured for comparing the amplified signal to at least one threshold value and to a reference value and for generating at least one output signal based on the comparison; and a feedback control module configured for generating the control signal of the voltage amplifier based on the at least one output signal generated by the hysteresis comparing module.

Abstract: This invention relates to a pixel circuit comprising a photo-sensor stage (10) comprising a photodiode (1) delivering a photoreceptor current (Iph), a comparison stage (30) configured for detecting a change in a signal voltage (Vph) derived from said photoreceptor current, a sample-and-hold circuit (50) connected to the converting stage (20) and to the comparison stage (30), said comparison stage (30) configured to output an input signal for the sample-and-hold circuit (50), and for emitting a sampling signal to a control terminal of the sample-and-hold circuit (50) when a change is detected in the signal voltage (Vph).

Abstract: A method of performing unsupervised detection of repeating patterns in a series (TS) of events (E21, E12, E5 . . . ), comprising the steps of: a) Providing a plurality of neurons (NRI-NRP), each neuron being representative of W event types; b) Acquiring an input packet (IV) comprising N successive events of the series; c) Attributing to at least some neurons a potential value (PTI-PTP), representative of the number of common events between the input packet and the neuron; d) Modify the event types of neurons having a potential value exceeding a first threshold TL; and e) generating a first output signal (OSI-OSP) for all neurons having a potential value exceeding a second threshold TF, and a second output signal, different from the first one, for all other neurons. A digital electronic circuit and system configured for carrying out such a method.

Abstract: This invention relates to a pixel circuit comprising a photo-sensor stage comprising a photodiode delivering a photoreceptor current, a comparison stage configured for detecting a change in a signal voltage derived from said photoreceptor current, a sample-and-hold circuit connected to the converting stage and to the comparison stage, said comparison stage configured to output an input signal for the sample-and-hold circuit, and for emitting a sampling signal to a control terminal of the sample-and-hold circuit when a change is detected in the signal voltage.

Abstract: A method of performing unsupervised detection of repeating patterns in a series of events, includes a) Providing a plurality of neurons, each neuron being representative of W event types; b) Acquiring an input packet comprising N successive events of the series; c) Attributing to at least some neurons a potential value, representative of the number of common events between the input packet and the neuron; d) Modify the event types of neurons having a potential value exceeding a first threshold TL; and e) generating a first output signal for all neurons having a potential value exceeding a second threshold TF, and a second output signal, different from the first one, for all other neurons. A digital electronic circuit and system configured for carrying out such a method is also provided.

Abstract: A pixel circuit for detecting time-dependent visual data includes a photo sensing device detecting a light intensity and generating a signal representing the detected light intensity. The pixel circuit further includes: a voltage amplifier configured for amplifying the signal representing the detected light intensity and generating an amplified signal, the amplified signal being generated by taking into account a control signal which shifts an input voltage offset of the voltage amplifier; a hysteresis comparing module configured for comparing the amplified signal to at least one threshold value and to a reference value and for generating at least one output signal based on the comparison; and a feedback control module configured for generating the control signal of the voltage amplifier based on the at least one output signal generated by the hysteresis comparing module.

Abstract: This invention relates to a pixel circuit comprising a photo-sensor stage (10) comprising a photodiode (1) delivering a photoreceptor current (Iph), a comparison stage (30) configured for detecting a change in a signal voltage (Vph) derived from said photoreceptor current, a sample-and-hold circuit (50) connected to the converting stage (20) and to the comparison stage (30), said comparison stage (30) configured to output an input signal for the sample-and-hold circuit (50), and for emitting a sampling signal to a control terminal of the sample-and-hold circuit (50) when a change is detected in the signal voltage (Vph).

Abstract: A neuron circuit performing synapse learning on weight values includes a first sub-circuit, a second sub-circuit, and a third sub-circuit. The first sub-circuit is configured to receive an input signal from a pre-synaptic neuron circuit and determine whether the received input signal is an active signal having an active synapse value. The second sub-circuit is configured to compare a first cumulative reception counter of active input signals with a learning threshold value based on results of the determination. The third sub-circuit is configured to perform a potentiating learning process based on a first probability value to set a synaptic weight value of at least one previously received input signal to an active value, upon the first cumulative reception counter reaching the learning threshold value, and perform a depressing learning process based on a second probability value to set each of the synaptic weight values to an inactive value.

Abstract: The invention relates to a transimpedance gain circuit for temporally differentiating photo-sensing systems in dynamic vision sensors, which uses at least one photodiode and at least two in-series transistors, each of the transistors being connected in diode configuration and being positioned at the output of the photodiode. The output current from the photodiode flows through the drain-source channels of the transistors and the source of the last transistor in series is connected to a voltage selected from ground voltage, a constant voltage or a controlled voltage.

Abstract: The invention relates to a method and a device for detecting the temporal variation of the light intensity in a matrix of photosensors, comprising a matrix of pixels, a block for the automatic adjustment of the amplification of the photocurrent, and an arbitrating and event-encoding block. Each pixel comprises a photosensor that generates a photocurrent, an adjustable gain current mirror connected to the outlet of the photosensor, a transimpedance amplifier arranged at the outlet of the current mirror, optionally at least one amplification circuit arranged at the outlet of the transimpedance amplifier, and capacitors and detectors of thresholds for determining whether the output voltage exceeds a higher threshold or drops below a lower threshold in order to generate an event in the pixel.

Abstract: The invention relates to a method and a device for detecting the temporal variation of the light intensity in a matrix of photosensors, comprising a matrix of pixels, a block for the automatic adjustment of the amplification of the photocurrent, and an arbitrating and event-encoding block. Each pixel comprises a photosensor that generates a photocurrent, an adjustable gain current mirror connected to the outlet of the photosensor, a transimpedance amplifier arranged at the outlet of the current mirror, optionally at least one amplification circuit arranged at the outlet of the transimpedance amplifier, and capacitors and detectors of thresholds for determining whether the output voltage exceeds a higher threshold or drops below a lower threshold in order to generate an event in the pixel.

Abstract: The invention solves the technical problem associated with finding a way of making contributions as if using dynamic synapses, but using the simplest neural circuits possible, such as with instantaneous integration synapses. In this way, each neuron would be capable of making the correct decision, thereby allowing correct recognition on the part of the neural network. For this purpose, each input pulse is replaced with a train of “r” pulses and the “weight” value is attenuated by a value in the vicinity of “r”. The “r” pulses are spaced apart for a characteristic time. The spacing of the “r” pulses may or may not be equidistant. Consequently, if a front of simultaneous pulses arrives at the neuron, originating from multiple neurons in the preceding layer, the trains of pulses are interleaved with one another and they all contribute to the decision of the neuron as to whether or not it should be activated.

Abstract: The invention relates to a low-mismatch and low-consumption transimpedance gain circuit for temporally differentiating photo-sensing systems in dynamic vision sensors, which uses at least one photodiode and at least two in-series transistors, each of the transistors being connected in diode configuration and being positioned at the output of the photodiode. The output current from the photodiode flows through the drain-source channels of the transistors and the source of the last transistor in series is connected to a voltage selected from ground voltage, a constant voltage or a controlled voltage.