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 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 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 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 method for forming a current collector is provided. At least two carbon nanostructure reinforced copper composite substrates are provided. The at least two carbon nanostructure reinforced copper composite substrates are stacked to form a composite substrate. An active metal layer is disposed on a surface of the composite substrate to form a first a composite structure. The first composite structure is pressed to form a second composite structure. The second composite structure is annealed to form a third composite structure. The third composite structure is de-alloyed to form a porous copper composite.

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.

Abstract: An aluminum matrix composite is provided. The aluminum matrix composite comprises at least one reinforcement layer and an aluminum layer. The at least one reinforcement layer comprises a plurality of reinforcement sheets. The plurality of reinforcement sheets are uniformly dispersed in at least a portion of the aluminum layer.

Abstract: A method for forming a porous copper composite is provided. At least two carbon nanostructure reinforced copper composite substrates are provided. The at least two carbon nanostructure reinforced copper composite substrates are stacked to form a composite substrate. An active metal layer is disposed on a surface of the composite substrate to form a first a composite structure. The first composite structure is pressed to form a second composite structure. The second composite structure is annealed to form a third composite structure. The third composite structure is de-alloyed to form a porous copper composite.

Abstract: An anode of the lithium ion battery is provided. The anode of the lithium ion battery comprises a nanoporous copper substrate and a copper oxide nanosheet array. The copper oxide nanosheet array is disposed on one surface of the nanoporous copper substrate, and the nanoporous copper substrate is chemically bonded to the copper oxide nanosheet array.

Abstract: A method for making nanoporous nickel composite material comprises: providing a cathode plate and a copper-containing anode plate, electroplating a copper material layer a surface of the cathode plate; laying a carbon nanotube layer on the copper material layer, and forming an overlapped structure of the copper material layer and the carbon nanotube laye; the cathode plate and the overlapped structure are used as a cathode, and a nickel-containing anode plate is used as an anode, plating a nickel material layer on the overlapped structure to form sandwich structure; repeating steps S1 to S3 to obtain a carbon nanotube-reinforced copper-nickel alloy; rolling and annealing the carbon nanotube-reinforced copper-nickel alloy; and etching the carbon nanotube-reinforced copper-nickel alloy to form the nanoporous nickel composite material.

Abstract: An aluminum matrix composite is provided. The aluminum matrix composite comprises at least one reinforcement layer and an aluminum layer. The at least one reinforcement layer comprises a plurality of reinforcement sheets.

Abstract: A method for forming an aluminum matrix composite is provided. At least one reinforcement layer and an aluminum layer are provided. The at least one reinforcement layer is disposed on at least one surface of the aluminum layer to form a first composite structure. The first composite structure is pressed to form a second composite structure. A process of alternatively folding and pressing the second composite structure is repeated to form the aluminum matrix composite.

Abstract: A method of making a nanoporous copper is provided. A copper alloy layer and at least one active metal layer are provided. The copper alloy layer comprises a first surface and a second surface. The at least one active metal layer is located on the first surface and the second surface to form a structure. The structure is processed to form a composite structure. A process of folding and pressing the composite structure is repeated to form a precursor. The precursor is corroded to form the nanoporous copper.

Abstract: A method for making nanoporous nickel composite material comprises: providing a cathode plate and a copper-containing anode plate, electroplating a copper material layer a surface of the cathode plate; laying a carbon nanotube layer on the copper material layer, and forming an overlapped structure of the copper material layer and the carbon nanotube laye; the cathode plate and the overlapped structure are used as a cathode, and a nickel-containing anode plate is used as an anode, plating a nickel material layer on the overlapped structure to form sandwich structure; repeating steps S1 to S3 to obtain a carbon nanotube-reinforced copper-nickel alloy; rolling and annealing the carbon nanotube-reinforced copper-nickel alloy; and etching the carbon nanotube-reinforced copper-nickel alloy to form the nanoporous nickel composite material.

Abstract: A method for forming a porous copper composite is provided. At least two carbon nanostructure reinforced copper composite substrates are provided. The at least two carbon nanostructure reinforced copper composite substrates are stacked to form a composite substrate. An active metal layer is disposed on a surface of the composite substrate to form a first a composite structure. The first composite structure is pressed to form a second composite structure. The second composite structure is annealed to form a third composite structure. The third composite structure is de-alloyed to form a porous copper composite.

Abstract: A method for forming a current collector is provided. At least two carbon nanostructure reinforced copper composite substrates are provided. The at least two carbon nanostructure reinforced copper composite substrates are stacked to form a composite substrate. An active metal layer is disposed on a surface of the composite substrate to form a first a composite structure. The first composite structure is pressed to form a second composite structure. The second composite structure is annealed to form a third composite structure. The third composite structure is de-alloyed to form a porous copper composite.

Abstract: A method for forming an aluminum matrix composite is provided. At least one reinforcement layer and an aluminum layer are provided. The at least one reinforcement layer is disposed on at least one surface of the aluminum layer to form a first composite structure. The first composite structure is pressed to form a second composite structure. A process of alternatively folding and pressing the second composite structure is repeated to form the aluminum matrix composite.