Abstract: Methods and apparatus are provided for memorizing data signals in a spiking neural network. For each data signal, such a method includes supplying metadata relating to the data signal to a machine learning model trained to generate an output signal, indicating a relevance class for a data signal, from input metadata for that data signal. The method includes iteratively supplying the data signal to a sub-assembly of neurons, interconnected via synaptic weights, of a spiking neural network and training the synaptic weights to memorize the data signal in the sub-assembly. The method further comprises assigning neurons of the network to the sub-assembly in dependence on the output signal of the model such that more relevant data signals are memorized by larger sub-assemblies. The data signal memorized by a sub-assembly can be subsequently recalled by activating neurons of that sub-assembly.

Abstract: Neuron circuits are provided for spiking neural network apparatus having multiple such neuron circuits interconnected by links, each associated with a respective weight, for transmission of signals between neuron circuits. A neuron circuit includes a digital transmitter for generating trigger signals, indicating a state of the neuron circuit, on outgoing links of the circuit. The state is encoded in a time interval defined by these trigger signals. The neuron circuit includes a digital receiver for detecting such trigger signals on incoming links of the circuit, and digital accumulator logic. In response to detecting a trigger signal on an incoming link, the digital accumulator logic is adapted to generate a weighted signal dependent on the time interval and to accumulate the weighted signals generated from trigger signals on the incoming links to determine the state of the neuron circuit.

Abstract: A computer-implemented method for managing datasets of a storage system is provided, wherein the datasets have respective sets of metadata, the method including: successively feeding first sets of metadata to a spiking neural network (SNN), the first sets of metadata fed corresponding to datasets of the storage system that are labeled with respect to classes they belong to, so as to be associated with class labels, for the SNN to learn representations of said classes in terms of connection weights that weight the metadata fed; successively feeding second sets of metadata to the SNN, the second sets of metadata corresponding to unlabeled datasets of the storage system, for the SNN to infer class labels for the unlabeled datasets, based on the second sets of metadata fed and the representations learned; and managing datasets in the storage system, based on class labels of the datasets, these including the inferred class labels.

Abstract: Predefined concepts are represented by codebooks. Each codebook includes candidate code hypervectors that represent items of a respective concept of the predefined concepts. A neuromorphic memory device with a crossbar array structure includes row lines and column lines stores a value of respective code hypervectors of an codebook. An input hypervector is stored in an input buffer. A plurality of estimate buffers are each associated with a different subset of row lines and a different codebook and initially store estimated hypervectors. An unbound hypervector is computed using the input hypervector and all the estimated hypervectors. An attention vector is computed that indicates a similarity of the unbound hypervector with one estimated hypervector. A linear combination of the one estimated hypervector, weighted by the attention vector, is computed and is stored in the estimate buffer that is associated with the one estimated hypervector.

Abstract: A computer-implemented method for performing a classification of an input signal utilizing a neural network includes: computing, by a feature extraction unit of the neural network, a query vector; and performing, by a classification unit, a factorization of the query vector to a plurality of codebook vectors of a plurality of codebooks to determine a corresponding class of a number of classes. A set of combinations of vector products of the plurality of codebook vectors of the plurality of codebooks establishes a number of classes of the classification unit.

Abstract: A computer-implemented method for performing a classification of an input signal by a neural network includes: computing, by a feature extraction unit of the neural network, a D-dimensional query vector, wherein D is an integer; generating, by a classification unit of the neural network, a set of C fixed D-dimensional quasi-orthogonal bipolar vectors as a fixed classification matrix, wherein C is an integer corresponding to a number of classes of the classification unit; and performing a classification of a query vector based, at least in part, on the fixed classification matrix.

Abstract: A computer-implemented method for factorizing hypervectors in a resonator network includes: receiving an input hypervector representing a data structure; performing an iterative process for each concept in a set of concepts associated with the data structure in order to factorize the input hypervector into a plurality of individual hypervectors representing the set of concepts, wherein the iterative process includes: generating a first estimate of an individual hypervector representing a concept in the set of concepts; generating a similarity vector indicating a similarity of the estimate of the individual hypervector with each candidate attribute hypervector of a plurality of candidate attribute hypervectors representing an attribute associated with the concept; and generating a second estimate of the individual hypervector based, at least in part, on a linear combination of the plurality of candidate attribute hypervectors and performing a non-linear function on the linear combination of the plurality of ca

Abstract: A system for hyper-dimensional computing for inference tasks may be provided. The device comprises an item memory for storing hyper-dimensional item vectors, a query transformation unit connected to the item memory, the query transformation unit being adapted for forming a hyper-dimensional query vector from a query input and hyper-dimensional base vectors stored in the item memory, and an associative memory adapted for storing a plurality of hyper-dimensional profile vectors and for determining a distance between the hyper-dimensional query vector and the plurality of hyper-dimensional profile vectors, wherein the item memory and the associative memory are adapted for in-memory computing using memristive devices.

Abstract: The present disclosure relates to a method for representing an ordered group of symbols with a hypervector. The method comprises sequentially applying on at least part of the input hypervector associated with a current symbol a predefined number of circular shift operations associated with the current symbol, resulting in a shifted hypervector. A rotate operation may be applied on the shifted hypervector, resulting in an output hypervector. If the current symbol is not the last symbol of the ordered group of symbols the output hypervector may be provided as the input hypervector associated with a subsequent symbol of the current symbol; otherwise, the output hypervector of the last symbol of the ordered group of symbols may be provided as a hypervector that represents the ordered group of symbols.

Abstract: A computer-implemented method for classification of an input element to an output class in a spiking neural network may be provided. The method comprises receiving an input data set comprising a plurality of elements, identifying a set of features and corresponding feature values for each element of the input data set, and associating each feature to a subset of spiking neurons of a set of input spiking neurons of the spiking neural network. Furthermore, the method comprises also generating, by the input spiking neurons, spikes at pseudo-random time instants depending on a value of the feature for a given input element, and classifying an element into a class depending on a distance measure value between output spiking patterns at output spiking neurons of the spiking neural network and a predefined target pattern related to the class.

Abstract: The present disclosure relates to a method for classifying a query information element using the similarity between the query information element and a set of support information elements. A resulting set of similarity scores is transformed using a sharpening function such that the transformed scores are decreasing as negative similarity scores increase and the transformed scores are increasing as positive similarity scores increase. A class of the query information element is determined based on the transformed similarity scores.

Abstract: A computer-implemented method, system, and computer program product to solve a cognitive task that includes learning abstract properties. One embodiment may comprise accessing datasets that characterize the abstract properties. The accessed datasets may then be inputted into a first neural network to generate first embeddings. Pairs of the first embeddings generated may be formed, which correspond to pairs of the datasets. Data corresponding to the pairs formed may then be inputted into a second neural network, which may be executed to generate second embeddings. The latter may capture relational properties of the pairs of the datasets. A third neural network may be subsequently executed, based on the second embeddings generated, to obtain output values. One or more abstract properties of the datasets are learned based on the output values obtained, in order to solve the cognitive task.

Abstract: The invention is directed to a device for high-dimensional encoding of a plurality of sequences of quantitative data signals. The device comprises a plurality of input channels for receiving the plurality of sequences of quantitative data signals and an encoding unit. The encoding unit is configured to perform a temporal high-dimensional encoding of n-grams of the plurality of sequences of quantitative data signals; thereby creating a plurality of temporally encoded hypervectors for the plurality of input channels. The encoding unit is further configured to perform a spatial high-dimensional encoding of the plurality of temporally encoded hypervectors, thereby creating a temporally and spatially encoded hypervector. The device further comprises a configuration controller. The configuration controller is adapted to configure the high-dimensional encoding in dependence on one or more hyperparameter values.

Abstract: The invention is directed a device for high-dimensional encoding of a plurality of sequences of quantitative data signals. The device comprises a memory crossbar array comprising a plurality of resistive devices, a first peripheral circuit connected to the memory crossbar array, and a second peripheral circuit connected to the first peripheral circuit. The device is configured to receive the plurality of sequences of quantitative data signals via a plurality of input channels and to store elements of a plurality of precomputed basis hypervectors as conductance states of the resistive devices. The plurality of basis hypervectors are bound to respective input channels. The first peripheral circuit performs a temporal encoding of n-grams of the quantitative data signals thereby creating a plurality of temporally encoded hypervectors. The second peripheral circuit performs a spatial encoding of the plurality of temporally encoded hypervectors. This creates a temporally and spatially encoded hypervector.

Abstract: The invention is notably directed at a device for high-dimensional computing comprising an associative memory module. The associative memory module comprises one or more planar crossbar arrays. The one or more planar crossbar arrays comprise a plurality of resistive memory elements. The device is configured to program profile vector elements of profile hypervectors as conductance states of the resistive memory elements and to apply query vector elements of query hypervectors as read voltages to the one or more crossbar arrays. The device is further configured to perform a distance computation between the profile hypervectors and the query hypervectors by measuring output current signals of the one or more crossbar arrays. The invention further concerns a related method and a related computer program product.

Abstract: Methods and apparatus are provided for calculating branch metrics, associated with possible transitions between states of a trellis, in a sequence detector for detecting symbol values corresponding to samples of an analog signal transmitted over a channel. For each sample and each transition, the method calculates a plurality of distance values indicative of distance between that sample and respective hypothesized sample values for that transition. In parallel with calculation of the distance values, the sample is compared with a set of thresholds, each defined between a pair of successive hypothesized symbol values arranged in value order, to produce a comparison result. An optimum distance value is selected as a branch metric for the transition in dependence on the comparison result.

Abstract: Methods and apparatus are provided for implementing propagation of probability distributions of random variables over a factor graph. Such a method includes providing a spiking neural network, having variable nodes interconnected with factor nodes, corresponding to the factor graph. Each of the nodes comprises a set of neurons configured to implement computational functionality of that node. The method further comprises generating, for each of a set of the random variables, at least one spike signal in which the probability of a possible value of that variable is encoded via the occurrence of spikes in the spike signal, and supplying the spike signals for the set of random variables as inputs to the neural network at respective variable nodes. The probability distributions are propagated via the occurrence of spikes in signals propagated through the neural network.

Abstract: A storage system and a method for storing a data segment, a storage capacity manager and a method for managing a capacity of a storage unit, and a storage tier relocation manager and a method for relocating a data segment. The storage system includes at least two storage tiers, an access pattern evaluator, a classification unit, a selector, and logic. The storage capacitor manager includes a monitoring unit and capacity managing unit. The storage tier relocation manager includes a target storage tier, the data segment relocated to the target storage tier, and a protection measure.

Abstract: A computer-implemented method for classification of an input element to an output class in a spiking neural network may be provided. The method comprises receiving an input data set comprising a plurality of elements, identifying a set of features and corresponding feature values for each element of the input data set, and associating each feature to a subset of spiking neurons of a set of input spiking neurons of the spiking neural network. Furthermore, the method comprises also generating, by the input spiking neurons, spikes at pseudo-random time instants depending on a value of the feature for a given input element, and classifying an element into a class depending on a distance measure value between output spiking patterns at output spiking neurons of the spiking neural network and a predefined target pattern related to the class.

Abstract: A computer-implemented method, according to one embodiment, includes: receiving a first timestamp in response to a first servo reader detecting a stripe of a first servo burst on the magnetic tape, and receiving a second timestamp in response to a second servo reader detecting a stripe of a second servo burst on the magnetic tape. A third timestamp is received in response to the first servo reader detecting a stripe of a third servo burst on the magnetic tape, while a fourth timestamp is received in response to the second servo reader detecting a stripe of a fourth servo burst on the magnetic tape. The first, second, third, and fourth timestamps are used to determine the skew of the magnetic tape. Further still, the first and third servo bursts are in a same first servo sub-frame, while the second and fourth servo bursts are in a same second servo sub-frame.