Abstract: The present disclosure presents neural network learning systems and methods. One such method comprises receiving an input current signal; converting the input current signal to an input voltage pulse signal utilized by a memristive neuromorphic hardware of a multi-layered spiked neural network module; transmitting the input voltage pulse signal to the memristive neuromorphic hardware of the multi-layered spiked neural network module; performing a layer-by-layer calculation and conversion on the input voltage pulse signal to complete an on-chip learning to obtain an output signal; sending the output signal to a weight update circuitry module; and/or calculating, by the weight update circuitry module, an error signal and based on a magnitude of the error signal, triggering an adjustment of a conductance value of the memristive neuromorphic hardware so as to update synaptic weight values stored by the memristive neuromorphic hardware. Other methods and systems are also provided.

Abstract: A stuck-at fault mitigation method for resistive random access memory (ReRAM)-based deep learning accelerators, includes: confirming a distorted output value (Y0) due to a stuck-at fault (SAF) by using a correction data set in a pre-trained deep learning network, by means of ReRAM-based deep learning accelerator hardware; updating an average (?) and a standard deviation (?) of a batch normalization (BN) layer by using the distorted output value (Y0), by means of the ReRAM-based deep learning accelerator hardware; folding the batch normalization (BN) layer in which the average (?) and the standard deviation (?) are updated into a convolution layer or a fully-connected layer, by means of the ReRAM-based deep learning accelerator hardware; and deriving a normal output value (Y1) by using the deep learning network in which the batch normalization (BN) layer is folded, by means of the ReRAM-based deep learning accelerator hardware.

Abstract: Disclosed are various approaches for a controller that can generate and use non-stationary polar codes for encoding and decoding information. In one example, a method includes performing, by an encoder of the controller, a linear operation on at least one vector of information to be stored in a memory. The linear operation includes generating a polar encoded representation from the at least one vector of information. The linear operation also includes generating an output using at least one permutation that is based on a statistical characterization analysis of channels of the memory and a channel dependent permutation that is applied to the polar encoded representation. In some aspects, the statistical characterization analysis includes a respective reliability level of each one of the plurality of channels, and the channel dependent permutation includes an ordered permutation that orders the channels according to their respective reliability level.

Abstract: A stuck-at fault mitigation method for resistive random access memory (ReRAM)-based deep learning accelerators, includes: confirming a distorted output value (Y0) due to a stuck-at fault (SAF) by using a correction data set in a pre-trained deep learning network, by means of ReRAM-based deep learning accelerator hardware; updating an average (?) and a standard deviation (?) of a batch normalization (BN) layer by using the distorted output value (Y0), by means of the ReRAM-based deep learning accelerator hardware; folding the batch normalization (BN) layer in which the average (?) and the standard deviation (?) are updated into a convolution layer or a fully-connected layer, by means of the ReRAM-based deep learning accelerator hardware; and deriving a normal output value (Y1) by using the deep learning network in which the batch normalization (BN) layer is folded, by means of the ReRAM-based deep learning accelerator hardware.

Abstract: A system for tracking diet and nutrition includes an oral module configured to be affixed within a mouth of a user and including a set of salivary sensors responsive to a level of at least one nutrient. The system also includes a set of eating event sensors responsive to an eating event. The set of eating event sensors can be included in the oral module, or can be included in a body module configured to be affixed adjacent to a body part of the user.

Abstract: Disclosed are various approaches for a controller that can generate and use non-stationary polar codes for encoding and decoding information. In one example, a method includes performing, by an encoder of the controller, a linear operation on at least one vector of information to be stored in a memory. The linear operation includes generating a polar encoded representation from the at least one vector of information. The linear operation also includes generating an output using at least one permutation that is based on a statistical characterization analysis of channels of the memory and a channel dependent permutation that is applied to the polar encoded representation. In some aspects, the statistical characterization analysis includes a respective reliability level of each one of the plurality of channels, and the channel dependent permutation includes an ordered permutation that orders the channels according to their respective reliability level.

Abstract: A method of audio and video synchronization may include capturing an image by each of a plurality of cameras. The images and audio may be compared with each other for synchronization.

Abstract: A method of audio and video synchronization may include capturing an image by each of a plurality of cameras. The images and audio may be compared with each other for synchronization.

Abstract: A method and arrangement for reducing power consumption in an M row×N column array of processing cells. A row mask register masks individual cells in each row for being enabled. A column mask register masks individual cells in each column for being enabled. The combination of the row mask register signal and column mask register signal enables or disables each cell of the array. Enabled cells are activated to execute an operation or function, while disabled cells a prevented from consuming dynamic power. Depending on the application and enabled cells thereby, power consumption is reduced.

Abstract: A system and method for programming an M×N array of cells. Each cell is reconfigurable to execute a function according to a context instruction. The context instruction defines an operation of the array. An enable register includes a row enable register and a column enable register, corresponding to the M rows and N columns. Each cell is individually and independently enabled for receiving a next context instruction, according to an enable signal provided by the enable register. Non-enabled cells execute a present context. Enabled cells receive and execute an updated context. In this way, the array of cells can be configured to execute any number of independent functions for the operation.

Abstract: A method and arrangement for reducing power consumption in an M row×N column array of processing cells. A row mask register masks individual cells in each row for being enabled. A column mask register masks individual cells in each column for being enabled. The combination of the row mask register signal and column mask register signal enables or disables each cell of the array. Enabled cells are activated to execute an operation or function, while disabled cells a prevented from consuming dynamic power. Depending on the application and enabled cells thereby, power consumption is reduced.