Abstract: A method for generating a set of adversarial patches for an image. The method includes segmenting the image into a plurality of regions; selecting a set of target regions that satisfies an attacking criterion by discretely searching of the plurality of regions; and generating a set of adversarial patches by using the set of target regions.

Abstract: A computer-implemented method for generating training data includes (i) generating a basic shape, (ii) configuring the boundary conditions associated with a first partial differential equation (PDE) for the boundary of the basic shape, and (iii) determining a solution of the first PDE for the basic shape based on the basic shape and the boundary conditions, wherein the solution represents the physical state of an object having the basic shape. The training data is obtained based on the basic shape, the boundary conditions, and the solution.

Abstract: A computer-implemented method for determining the physical state of an object having a shape includes (i) dividing the shape of the object into a plurality of sub-shapes, (ii) obtaining a local solution for each of the plurality of sub-shapes through a neural network model based on a global boundary condition for the shape and the plurality of sub-shapes, wherein the local solution for each sub-shape represents the local physical state of the object having the sub-shape, and (ii) obtaining a global solution for the shape based on the local solution for each sub-shape in the plurality of sub-shapes, wherein the global solution for the shape represents the physical state of the object.

Abstract: The present disclosure provides recombinant adeno-associated virus (rAAV) virions with an engineered capsid protein. In particular, the disclosure provides AAV9 virions with engineered AAV9 capsid, AAV5/9 chimeric capsid or combinatory capsid that achieves increased transduction efficiency in cardiac cells, increased cell-type selectivity, and/or other desirable properties.

Abstract: In some aspects, the present disclosure provides engineered adeno-associated virus (AAV) capsid proteins comprising a non-naturally occurring amino acid motif described herein. In some embodiments, the present disclosure provides an AAV9, AAV5, AAVrh.10 or AAVrh.74-based engineered capsid protein, that when assembled into virions, achieves increased transduction efficiency of the heart, and/or other desirable properties. Also provided herein are recombinant AAV virions comprising any of the engineered capsid proteins described herein and uses thereof.

Abstract: Provided herein are capsids for plakophilin-2 (PKP2) gene therapy, including recombinant adeno-associated virus (rAAV) virions with an engineered capsid protein for treating heart diseases such as arrhythmogenic right ventricular cardiomyopathy (ARVC) or arrhythmogenic cardiomyopathy (ACM). In particular, the disclosure provides AAV9 virions encoding PKP2 with engineered AAV9 capsid, AAV5/9 chimeric capsid, or combinatory capsid that achieves increased transduction efficiency in heart, increased heart-to-liver ratio, and/or other desirable properties.

Abstract: The present disclosure provides engineered capsid proteins and recombinant adeno-associated virus (rAAV) virions with an engineered capsid protein. In particular, the disclosure provides AAV9 virions with engineered AAV9 capsid, AAV5/9 chimeric capsid, or combinatory capsid that achieves increased transduction efficiency in heart, increased heart-to-liver ratio, and/or other desirable properties.

Abstract: A method for deep learning. The method includes: receiving, by a deep learning model, a plurality of samples and a plurality of labels corresponding to the plurality of samples; adversarially augmenting, by the deep learning model, the plurality of samples based on a threat model; and assigning, by the deep learning model, a low predictive confidence to one or more adversarially augmented samples of the plurality of adversarially augmented samples having noisy labels due to the adversarially augmenting based on the threat model.

Abstract: A method for training a Neural Network (NN) model for imitating demonstrator's behavior. The method includes: obtaining demonstration data representing the demonstrator's behavior for performing a task, the demonstration data includes state data, action data and option data, wherein the state data correspond to a condition for performing the task, the option data correspond to subtasks of the task, and the action data correspond to the demonstrator's actions performed for the task; sampling learner data representing the NN model's behavior for performing the task based on a current learned policy; and updating the policy by using a generative adversarial imitation learning (GAIL) process based on the demonstration data and the learner data.

Abstract: A method for generating a set of adversarial patches for an image. The method includes segmenting the image into a plurality of regions; selecting a set of target regions that satisfies an attacking criterion by discretely searching of the plurality of regions; and generating a set of adversarial patches by using the set of target regions.

Abstract: A method for visual reasoning. The method includes: providing a network with sets of inputs and sets of outputs, wherein each set of inputs of the sets of inputs mapping to one of a set of outputs corresponding to the set of inputs based on visual information on the set of inputs, and wherein the network comprising a Probabilistic Generative Model (PGM) and a set of modules; determining a posterior distribution over combinations of one or more modules of the set of modules through the PGM, based on the provided sets of inputs and sets of outputs; and applying domain knowledge as one or more posterior regularization constraints on the determined posterior distribution.

Abstract: A method for training a deep neural network (DNN) capable of adversarial detection. The DNN is configured with a plurality of sets of weights candidates. The method includes inputting training data selected from training data set to the DNN. The method further includes calculating, based on the training data, a first term for indicating a difference between a variational posterior probability distribution and a true posterior probability distribution of the DNN. The method further includes perturbing the training data to generate perturbed training data; and calculating a second term for indicating a quantification of predictive uncertainty on the perturbed training data. The method further includes updating the plurality of sets of weights candidates of the DNN based on augmenting the summation of the first term and the second term.

Abstract: The present disclosure provides recombinant adeno-associated virus (rAAV) virions with an engineered capsid protein. In particular, the disclosure provides AAV9 virions with engineered AAV9 capsid, AAV5/9 chimeric capsid or combinatory capsid that achieves increased transduction efficiency in cardiac cells, increased cell-type selectivity, and/or other desirable properties.

Abstract: A computer-implemented training method for a convolutional neural network includes receiving first data and second data. The second data is data obtained after stylization is performed on the first data. The method further includes training the convolutional neural network based on the first data and the second data. The convolutional neural network has a first normalization layer and a second normalization layer. The first normalization layer is used for the first data, and the second normalization layer is used for the second data. The convolutional neural network trained in this way is no longer biased towards texture, and not only enhances robustness but also improves accuracy.