Abstract: A computer-implemented method for training a classifier, particularly a binary classifier, for classifying input signals to optimize performance according to a non-decomposable metric that measures an alignment between classifications corresponding to input signals of a set of training data and corresponding predicted classifications of the input signals obtained from the classifier. The method includes providing weighting factors that characterize how the non-decomposable metric depends on a plurality of terms from a confusion matrix of the classifications and the predicted classifications, and training the classifier depending on the provided weighting factors.

Abstract: A system and computer-implemented method are provided for training a dynamics model to learn the dynamics of a physical system. The dynamics model may be learned to be able to infer a future state of the physical system and/or its environment based on a current state of the physical system and/or its environment. The learned dynamics model is inherently globally stable. Instead of learning a dynamics model and attempting to separately verify its stability, the learnable dynamics model comprises a learnable Lyapunov function which is jointly learned together with the nominal dynamics of the physical system. The learned dynamics model is highly suitable for real-life applications in which a physical system may assume a state which was unseen during training as the learned dynamics model is inherently globally stable.

Abstract: A computer-implemented method for training a classifier. The method includes: ascertaining a first input signal characterizing a plurality of evaluation points of a molecular biological examination system, and a desired output signal characterizing a classification of the evaluation points is allocated to the first input signal; subdividing the first input signal into a plurality of second input signals according to an arrangement of the evaluation points; ascertaining a plurality of first representations, a first representation being ascertained for each second input signal of a first subset of the plurality of second input signals using the classifier; ascertaining an output signal using the classifier and based on the plurality of first representations, the output signal characterizing a classification of the first input signal; adapting at least one parameter of the classifier according to a loss value which characterizes a difference between the ascertained output signal and the desired output signal.

Abstract: Some embodiments are directed to a neural network training device for training a neural network. At least one layer of the neural network layers is a projection layer. The projection layer projects a layer input vector (x) of the projection layer to a layer output vector (y). The output vector (y) sums to the summing parameter (k).

Abstract: A system for applying a neural network to an input instance. The neural network includes an optimization layer for determining values of one or more output neurons from values of one or more input neurons by a joint optimization parametrized by one or more parameters. An input instance is obtained. The values of the one or more input neurons to the optimization layer are obtained and input vectors for the one or more input neurons are determined therefrom. Output vectors for the one or more output neurons are computed from the determined input vectors by jointly optimizing at least the output vectors with respect to the input vectors to solve a semidefinite program defined by the one or more parameters. The values of the one or more output neurons are determined from the respective computed output vectors.

Abstract: A system and computer implemented method for learning rules from a data base including entities and relations between the entities, wherein an entity is either a constant or a numerical value, and a relation between a constant and a numerical value is a numerical relation and a relation between two constants is a non-numerical relation. The method includes: deriving aggregate values from said numerical and/or non-numerical relations; deriving non-numerical relations from said aggregate values; adding said derived non-numerical relations to the data base; constructing differentiable operators, wherein a differentiable operator refers to a non-numerical or a derived non-numerical relation of the data base, and extracting rules from said differentiable operators.

Abstract: A system and method relate to providing machine learning predictions with defenses against patch attacks. The system and method include obtaining a digital image and generating a set of location data via a random process. The set of location data include randomly selected locations on the digital image that provide feasible bases for creating regions for cropping. A set of random crops is generated based on the set of location data. Each crop includes a different region of the digital image as defined in relation to its corresponding location data. The machine learning system is configured to provide a prediction for each crop of the set of random crops and output a set of predictions. The set of predictions is evaluated collectively to determine a majority prediction from among the set of predictions. An output label is generated for the digital image based on the majority prediction. The output label includes the majority prediction as an identifier for the digital image.

Abstract: A system and method is disclosed for labeling an unlabeled dataset, with a labeling budget constraint and noisy oracles (i.e. noisy labels provided by annotator), using a noisy labeled dataset from another domain or application. The system and method combine active learning with noisy labels and active learning with domain adaptation to enhance classification performance.

Abstract: A computer-implemented method includes applying a filter to input data based on an initial set of parameters to generate an initial feature map. The filter is configured to activate a filter function that involves a periodic function. The method includes performing a first linear transform on the initial feature map based on a subset of a first set of parameters to generate a first linear transform. The method includes applying the filter to the input data based on another subset of the first set of parameters to generate a first feature map. The method includes performing a multiplicative operation on the first linear transform and the first feature map to generate a first product. The method includes performing a second linear transform on the first product based on a subset of a second set of parameters to generate a second linear transform. The method includes generating output data that takes into account at least the second linear transform.

Abstract: Performing an adversarial attack on a neural network classifier is described. A dataset of input-output pairs is constructed, each input element of the input-output pairs randomly chosen from a search space, each output element of the input-output pairs indicating a prediction output of the neural network classifier for the corresponding input element. A Gaussian process is utilized on the dataset of input-output pairs to optimize an acquisition function to find a best perturbation input element from the dataset. The best perturbation input element is upsampled to generate an upsampled best input element. The upsampled best input element is added to an original input to generate a candidate input. The neural network classifier is queried to determine a classifier prediction for the candidate input. A score for the classifier prediction is computed. The candidate input is accepted as a successful adversarial attack responsive to the classifier prediction being incorrect.

Abstract: A system for training a classification model to be robust against perturbations of multiple perturbation types. A perturbation type defines a set of allowed perturbations. The classification model is trained by, in an outer iteration, selecting a set of training instances of a training dataset; selecting, among perturbations allowed by the multiple perturbation types, one or more perturbations for perturbing the selected training instances to maximize a loss function; and updating the set of parameters of the classification model to decrease the loss for the perturbed instances. A perturbation is determined by, in an inner iteration, determining updated perturbations allowed by respective perturbation types of the multiple perturbation types and selecting an updated perturbation that most increases the loss of the classification model.

Abstract: Markov random field parameters are identified to use for covariance modeling of correlation between gradient terms of a loss function of the classifier. A subset of images are sampled, from a dataset of images, according to a normal distribution to estimate the gradient terms. Black-box gradient estimation is used to infer values of the parameters of the Markov random field according to the sampling. Fourier basis vectors are generated from the inferred values. An original image is perturbed using the Fourier basis vectors to obtain loss function values. An estimate of a gradient is obtained from the loss function values. An image perturbation is created using the estimated gradient. The image perturbation is added to an original input to generate a candidate adversarial input that maximizes loss in identifying the image by the classifier. The neural network classifier is queried to determine a classifier prediction for the candidate adversarial input.

Abstract: A system and method relate to providing machine learning predictions with defenses against patch attacks. The system and method include obtaining a digital image and generating a set of location data via a random process. The set of location data include randomly selected locations on the digital image that provide feasible bases for creating regions for cropping. A set of random crops is generated based on the set of location data. Each crop includes a different region of the digital image as defined in relation to its corresponding location data. The machine learning system is configured to provide a prediction for each crop of the set of random crops and output a set of predictions. The set of predictions is evaluated collectively to determine a majority prediction from among the set of predictions. An output label is generated for the digital image based on the majority prediction. The output label includes the majority prediction as an identifier for the digital image.

Abstract: A computer-implemented method includes applying a filter to input data based on an initial set of parameters to generate an initial feature map. The filter is configured to activate a filter function that involves a periodic function. The method includes performing a first linear transform on the initial feature map based on a subset of a first set of parameters to generate a first linear transform. The method includes applying the filter to the input data based on another subset of the first set of parameters to generate a first feature map. The method includes performing a multiplicative operation on the first linear transform and the first feature map to generate a first product. The method includes performing a second linear transform on the first product based on a subset of a second set of parameters to generate a second linear transform. The method includes generating output data that takes into account at least the second linear transform.

Abstract: A simulation includes converting a molecular dynamics snapshot of elements within a multi-element system into a graph with atoms as nodes of the graph; defining a matrix such that each column of the matrix represents a node in the graph; defining a distance matrix according to a set of relative positions of each of the atoms; iterating through the GTFF using an attention mechanism, operating on the matrix and augmented by incorporating the distance matrix, to pass hidden state from a current layer of the GTFF to a next layer of the GTFF; performing a combination over the columns of the matrix to produce a scalar molecular energy; making a backward pass through the GTFF, iteratively calculating derivatives at each of the layers of the GTFF to compute a prediction of force acting on each atom; and returning the prediction of the force acting on each atom.

Abstract: A computer-implemented method for obtaining an adversarial input signal to a classifier for classifying input signals obtained from a sensor. The adversarial input signal is obtained from an original input signal. The adversarial input signal and the original input signal cause the classifier to classify the original input signal as belonging to a first class and the adversarial input signal as belonging to a second class different from said first class. The method includes: modifying said original input signal to yield a modified input signal; projecting said modified input signal onto a metric ball around said original input signal to yield a projected input signal; and obtaining said adversarial input signal depending on the projected input signal, characterized in that the metric is an at least approximate Wasserstein distance.

Abstract: A computer-implemented method for assessing a robustness of a smoothed classifier for classifying sensor signals received from a sensor. The method includes: providing an input signal depending on the sensor signal, determining, by the smoothed classifier, a first value which characterizes a probability that the input signal, when subjected to noise will be classified as belonging to a first class, wherein the first class is a most probable class, determining, by the smoothed classifier, a second value which characterizes a probability that the input signal, when subjected to the noise, will be classified as belonging to a second class, wherein the second class is a second-most probable class, determining a robustness value on a first inverse value of a standard Gaussian cumulative distribution function at the first value and/or depending on a second inverse value of the standard Gaussian cumulative distribution function at the second value.

Abstract: A controller for generating a control signal for a computer-controlled machine. A neural network may be applied to a current sensor signal, the neural network being configured to map the sensor signal to a raw control signal. A projection function may be applied to the raw control signal to obtain a stable control signal to control the computer-controllable machine.

Abstract: A computer-implemented method of configuring a system which interacts with a physical environment. An action of the system in a state of the physical environment results in an updated state of the physical environment according to a transition probability. A safe set of state-action pairs known to be safely performable and an unsafe set of state-action pairs to be avoided are indicated. During an environment interaction, a safe set of state-action pairs is updated by estimating a transition probability for a state-action pair based on an empirical transition probability of a similar other state-action pair, and including the state-action pair in the safe set of state-action pairs only if the state-action pair is not labelled as unsafe and the safe set of state-action pairs can be reached with sufficient probability from the state-action pair based on the estimated transition probability.

Abstract: A system and method is disclosed for labeling an unlabeled dataset, with a labeling budget constraint and noisy oracles (i.e. noisy labels provided by annotator), using a noisy labeled dataset from another domain or application. The system and method combine active learning with noisy labels and active learning with domain adaptation to enhance classification performance.