Abstract: A query-based generic end-to-end molecular optimization (“QMO”) system framework, method and computer program product for optimizing molecules, such as for accelerating drug discovery. The QMO framework decouples representation learning and guided search and applies to any plug-in encoder-decoder with continuous latent representations. QMO framework directly incorporates evaluations based on chemical modeling, analysis packages, and pre-trained machine-learned prediction models for efficient molecule optimization using a query-based guided search method based on zeroth order optimization. The QMO features efficient guided search with molecular property evaluations and constraints obtained using the predictive models and chemical modeling and analysis packages.

Abstract: A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations. The operations may include receiving an input, extracting features from the input, and mining object relations using the features. The operations may include determining feature vectors using the object relations and generating, using the feature vectors, an output indicating a target region, wherein the target region corresponds to the input.

Abstract: Aspects of the invention include techniques for improving the accuracy of access-limited neural network inference in low-voltage regimes. A non-limiting example method includes training a first machine learning model to perform input transformation for reducing low-voltage bit errors for a deep neural network operating in a low-voltage regime. The training includes inputting training data into the first machine learning model such that, in response, the first machine learning model produces transformed training data; inputting the transformed training data into a clean machine learning model and into perturbed machine learning models, the perturbed machine learning models being generated by applying random bit errors to the clean machine learning model; and optimizing the first machine learning model based on a comparison of output of the clean machine learning model and of the perturbed machine learning models compared to groundtruth labels for the training data.

Abstract: A machine learning model is trained using original source domain data through empirical risk minimization and a model sensitivity map is computed. Each sensitive frequency point on the model sensitivity map is targeted. An adversarial technique is employed to generate spectral adversarial images based on the model sensitivity map and an image amplitude spectrum is augmented. The generated spectral adversarial images are mixed with the original source domain data to finetune the machine learning model and deployment of the finetuned machine learning model is facilitated.

Abstract: In a method of machine learning inferencing, access, via a computer, raw data including data elements; and produce, via the computer, a respective positional encoding vector for each of the data elements. The producing includes computing coefficients using a discrete functional transform on a sequence of the data elements in the raw data. Produce, via the computer, one or more representational encoding vectors based upon the positional encoding vectors and that represent the raw data. Input via the computer, the one or more representational encoding vectors into a neural network. In response to the inputting, receive, via the computer, output from the neural network. The output includes an inference related to the raw data.

Abstract: An adversarial robustness testing method, system, and computer program product include testing, via an accelerator, a robustness of a black-box system under different access settings, where the testing includes tearing down the robustness testing to a subtask of a predetermined size.

Abstract: Techniques regarding generating a synthetic dataset of objects are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can include a defining component that can define a tractable forward process associated with a diffusion model, with defining the tractable forward process including inputting noise to compromise training data, resulting in compromised training data. The computer executable components can further include a training component that, using the compromised training data, trains the diffusion model to reverse process the tractable forward process, wherein the training results in a compromised diffusion model.

Abstract: Some embodiments of the present disclosure are directed to systems, computer-readable media, and computer-implemented methods for neural network training. Some embodiments are directed to determining an attack order schedule for the data sample that includes a plurality of adversarial perturbation attacks associated with the data sample, and performing a composite adversarial attack process against the data set using the determined attack order schedule to generate a perturbed data sample for the data sample. Other embodiments may be disclosed or claimed.

Abstract: A common mode filter includes a first iron core, a second iron core, a first coil, and a second coil. The first iron core includes two first electrode portions and two second electrode portions. The second iron core is disposed above the first iron core, and the first iron core and the second iron core are adhered to each other. All surfaces of the second iron core are coated with an insulating layer. The first coil is wound around the first iron core and the second iron core. The second coil is wound around the first iron core and the second iron core.

Abstract: Some embodiments of the present disclosure are directed to systems, computer-readable media, and computer-implemented methods for neural network calibration. Some embodiments are directed to determining a universal perturbation value and temperature scaling parameter based on a training data set, and processing a testing data set using a neural network by applying the universal perturbation value to the testing data set, and applying the temperature scaling parameter to a plurality of logits determined by the neural network based on the testing data set. Other embodiments may be disclosed or claimed.

Abstract: Provided are a computer program product, system, and method for training a pose estimation model to determine anatomy keypoints in images. A teacher network, implementing machine learning, processes images representing anatomies to produce heatmaps representing keypoints of the anatomies. An anatomy parsing network, implementing machine learning, processes the images to produce segmentation representations labeling anatomies represented in the images. The segmentation representations from the anatomy parsing network and the heatmaps from the teacher network are concatenated to produce mixed heatmaps. A pose estimation model, implementing machine learning, is trained to process the images to output predicted heatmaps to minimize a loss function of the output predicted heatmaps from the pose estimation model and the mixed heatmaps.

Abstract: A first language vector can be generated by performing a first linear projection on a partial amino acid sequence vector. A second language vector can be generated by performing natural language processing on the first language vector. A predicted amino acid sequence vector can be generated by performing a second linear projection on the second language vector. A complete amino acid sequence listing can be output based on the predicted amino acid sequence vector.

Abstract: Techniques of video processing for action detection using machine learning. An action depicted in a video is identified. A type of the action is predicted based on a classification module of one or more machine learning models. A video clip depicting the action is predicted in the video. To that end, a starting point and an ending point of the video clip in the video are determined. The video clip is predicted based on a localization module of the one or more machine learning models. A refinement is performed that includes refining the type of the action based on the video clip or refining the video clip based on the type of the action. An indication of the refined type or of the refined video clip is output.

Abstract: Transfer learning in machine learning can include receiving a machine learning model. Target domain training data for reprogramming the machine learning model using transfer learning can be received. The target domain training data can be transformed by performing a transformation function on the target domain training data. Output labels of the machine learning model can be mapped to target labels associated with the target domain training data. The transformation function can be trained by optimizing a parameter of the transformation function. The machine learning model can be reprogrammed based on input data transformed by the transformation function and a mapping of the output labels to target labels.

Abstract: Systems and techniques that facilitate reprogrammable federated learning are provided. In various embodiments, a server device can share a pre-trained and frozen neural network with a set of client devices. In various aspects, the server device can orchestrate reprogrammable federated learning of the pre-trained and frozen neural network among the set of client devices. In various instances, the pre-trained and frozen neural network can be positioned between at least one trainable input layer and at least one trainable output layer, and the reprogrammable federated learning can involve the at least one trainable input layer and the at least one trainable output layer, but not the pre-trained and frozen neural network, being locally adjusted by the set of client devices.

Abstract: A multi-phase coupled inductor includes a first iron core, a second iron core, and a plurality of coil windings. The first iron core includes a first body and a plurality of first core posts. The plurality of first core posts are connected to the first body. The second iron core is opposite to the first iron core. The second iron core and the first body are spaced apart from each other by a gap. The plurality of coil windings wrap around the plurality of first core posts, respectively. Each of the coil windings has at least two coils.

Abstract: Techniques to fine-tune a joint text-image encoder via model reprogramming. The joint text-image encoder includes an image encoder and a text encoder, which are trained. An image and a caption describing the image are received. A reprogrammed image is generated based on the received image and using a first function. A reprogrammed caption is generated based on the received caption and using a second function. The image encoder and the text encoder are further trained using the reprogrammed image and the reprogrammed caption. One or more parameters for each of the first and second functions are backpropagated to produce, via transfer learning, the fine-tuned joint text-image encoder.

Abstract: One or more computer processors improve action recognition by removing inference introduced by visual appearances of objects within a received video segment. The one or more computer processors extract appearance information and structure information from a received video segment. The one or more computer processors calculate a factual inference (TE) for the received video segment utilizing the extracted appearance information and structure information. The one or more computer processors calculate a counterfactual debiasing inference (NDE) for the received video segment. The one or more computer processors calculate a total indirect effect (TIE) by subtracting the calculated counterfactual debiased inference from the calculated factual inference. The one or more computer processors action recognize the received video segment by selecting a classification result associated with a highest calculated TIE.

Abstract: A multi-phase coupled inductor includes a first iron core, a second iron core, and a plurality of coil windings. The first iron core includes a first body and a plurality of first core posts. The plurality of first core posts are connected to the first body. The second iron core is opposite to the first iron core. The second iron core and the first body are spaced apart from each other by a gap. The plurality of coil windings wrap around the plurality of first core posts, respectively. Each of the coil windings has at least two coils.

Abstract: A computer implemented method for certifying robustness of image classification in a neural network is provided. The method includes initializing a neural network model. The neural network model includes a problem space and a decision boundary. A processor receives a data set of images, image labels, and a perturbation schedule. Images are drawn from the data set in the problem space. A distance from the decision boundary is determined for the images in the problem space. A re-weighting value is applied to the images. A modified perturbation magnitude is applied to the images. A total loss function for the images in the problem space is determined using the re-weighting value. A confidence level of the classification of the images in the data set is evaluated for certifiable robustness.