Abstract: Implementations disclosed herein are directed to techniques for enabling decentralized learning of global language models (LMs). Remote processor(s) of a remote system can obtain a global LM that includes a global embedding matrix, generate a global embedding mask for the global embedding matrix using a masking technique, apply the global embedding mask to global embedding matrix to generate a sparsified global LM that includes a masked global embedding matrix that is a masked version of the global embedding matrix, transmit the sparsified global LM to computing device(s) that are participating in a given round of decentralized learning for the global language model, receive corresponding updates from the computing device(s), and cause the global LM to be updated based on the corresponding updates. By generating the global embedding mask and applying it to the global embedding matrix, the transferable size of the global LM is reduced thereby enabling decentralized learning thereof.

Abstract: The present disclosure provides a liquid cooling assembly and a liquid cooling apparatus. The liquid cooling assembly includes: two heat conducting plates, configured to perform heat dissipation on a storage module attached to each of the heat conducting plates; a liquid cooling tube, disposed on an end of the each heat conducting plates and configured to perform liquid cooling on the heat conducting plates; and an elastic support, disposed between the two heat conducting plates and configured to apply elastic pressure to the heat conducting plates during attachment between the heat conducting plates and the storage modules, to cause the heat conducting plates to be tightly attached to surfaces of the storage modules, and cause the storage modules to be easily separated from the heat conducting plates after the elastic support is removed from the two heat conducting plates.

Abstract: A method includes receiving distillation data including a plurality of out-of-domain training utterances. For each particular out-of-domain training utterance of the distillation data, the method includes generating a corresponding augmented out-of-domain training utterance, and generating, using a teacher ASR model trained on training data corresponding to a target domain, a pseudo-label corresponding to the corresponding augmented out-of-domain training utterance. The method also includes distilling a student ASR model from the teacher ASR model by training the student ASR model using the corresponding augmented out-of-domain training utterances paired with the corresponding pseudo-labels generated by the teacher ASR model.

Abstract: Information can be distilled from a global automatic speech recognition (ASR) model to a client ASR model. Many implementations include using an RNN-T model as the ASR model, where the global ASR model includes a global encoder, a joint network, a prediction network, and where the client ASR model includes a client encoder, the joint network, and the prediction network. Various implementations include using principal component analysis (PCA) while training the global ASR model to learn a mean vector and a set of principal components corresponding to the global ASR model. Additional or alternative implementations include training the client ASR model to generate one or more predicted coefficients of the global ASR model.

Abstract: A method includes receiving distillation data including a plurality of out-of-domain training utterances. For each particular out-of-domain training utterance of the distillation data, the method includes generating a corresponding augmented out-of-domain training utterance, and generating, using a teacher ASR model trained on training data corresponding to a target domain, a pseudo-label corresponding to the corresponding augmented out-of-domain training utterance. The method also includes distilling a student ASR model from the teacher ASR model by training the student ASR model using the corresponding augmented out-of-domain training utterances paired with the corresponding pseudo-labels generated by the teacher ASR model.

Abstract: Implementations described herein identify and correct automatic speech recognition (ASR) misrecognitions. For example, on-device processor(s) of a client device may generate a predicted textual segment that is predicted to correspond to spoken utterance of a user of the client device, and may receive further input that modifies the predicted textual segment to an alternate textual segment. Further, the on-device processor(s) may store these textual segments in on-device storage as a candidate correction pair, and transmit the candidate correction pair to a remote system. Moreover, remote processor(s) of the remote system may determine that the candidate correction pair is an actual correction pair, and may cause client devices to generate updates for a global ASR model for the candidate correction pair. Additionally, the remote processor(s) may distribute the global ASR model to the client devices and/or additional client devices.

Abstract: Example aspects of the present disclosure provide a novel, resource-efficient approach for federated machine learning techniques with PTNs. The system can determine a first set of training parameters from a plurality of parameters of the global model. Additionally, the system can generate a random seed, using a random number generator, based on a set of frozen parameters. Moreover, the system can transmit, respectively to a plurality of client computing devices, a first set of training parameters and the random seed. Furthermore, the system can receive, respectively from the plurality of client computing devices, updates to one or more parameters in the first set of training parameters. Subsequently, the system can aggregate the updates to one or more parameters that are respectively received from the plurality of client computing devices. The system can modify one or more global parameters of the global model based on the aggregation.

Abstract: The present disclosure discloses polyester composites and their preparation methods, and belongs to the technical field of polymer processing and modification. The polyester composites of the present disclosure comprise 65 to 90 parts of polyester, 5 to 35 parts of an elastomer, 0.05 to 3 parts of a chain extender and 0.01 to 5 parts of a functional additive. The polyester composites of the present disclosure not only have ultra-high toughness, but also can maintain high tensile strength, have excellent hydrolysis resistance, can be matched with an antibacterial agent or an antistatic agent to have good antibacterial or antistatic additional functions, can be widely applied to the fields of fibers and fabrics, plastic structural parts, plastic packages or automobile interior parts, and have a wide prospect.

Abstract: Methods and systems for artificial intelligence based medical image segmentation are disclosed. In a method for autonomous artificial intelligence based medical image segmentation, a medical image of a patient is received. A current segmentation context is automatically determined based on the medical image and at least one segmentation algorithm is automatically selected from a plurality of segmentation algorithms based on the current segmentation context. A target anatomical structure is segmented in the medical image using the selected at least one segmentation algorithm.

Abstract: The invention discloses a preparation method of a catechol group modified biomacromolecular scaffold material, comprising: grafting a catechol-containing compound by amidation to obtain modified biomacromolecules; then, allowing dopamine to perform oxidized self-polymerization in a weakly alkaline buffer solution to form polydopamine (PDA) particles with a uniform particle size; next, forming a scaffold which has three cross-linking structures, namely modified biomacromolecules, modified biomacromolecules/PDA, and biomacromolecules/PDA, through interaction between catechol groups, interaction between catechol groups and PDA particles, and interaction between macromolecules and PDA particles in the modified macromolecules respectively; and cross-linking the scaffold with calcium ions, adipic dihydrazide or genipin to further adjust the degree of cross-linking and porosity of the scaffold.

Abstract: Systems and methods are provided for performing medical imaging analysis. Input medical imaging data is received for performing a particular one of a plurality of medical imaging analyses. An output that provides a result of the particular medical imaging analysis on the input medical imaging data is generated using a neural network trained to perform the plurality of medical imaging analyses. The neural network is trained by learning one or more weights associated with the particular medical imaging analysis using one or more weights associated with a different one of the plurality of medical imaging analyses. The generated output is outputted for performing the particular medical imaging analysis.

Abstract: Methods and apparatus for automated medical image analysis using deep learning networks are disclosed. In a method of automatically performing a medical image analysis task on a medical image of a patient, a medical image of a patient is received. The medical image is input to a trained deep neural network. An output model that provides a result of a target medical image analysis task on the input medical image is automatically estimated using the trained deep neural network. The trained deep neural network is trained in one of a discriminative adversarial network or a deep image-to-image dual inverse network.

Abstract: Methods and systems for artificial intelligence based medical image segmentation are disclosed. In a method for autonomous artificial intelligence based medical image segmentation, a medical image of a patient is received. A current segmentation context is automatically determined based on the medical image and at least one segmentation algorithm is automatically selected from a plurality of segmentation algorithms based on the current segmentation context. A target anatomical structure is segmented in the medical image using the selected at least one segmentation algorithm.

Abstract: Methods and systems for artificial intelligence based medical image segmentation are disclosed. In a method for autonomous artificial intelligence based medical image segmentation, a medical image of a patient is received. A current segmentation context is automatically determined based on the medical image and at least one segmentation algorithm is automatically selected from a plurality of segmentation algorithms based on the current segmentation context. A target anatomical structure is segmented in the medical image using the selected at least one segmentation algorithm.

Abstract: The present disclosure discloses polyester composites and their preparation methods, and belongs to the technical field of polymer processing and modification. The polyester composites of the present disclosure comprise 65 to 90 parts of polyester, 5 to 35 parts of an elastomer, 0.05 to 3 parts of a chain extender and 0.01 to 5 parts of a functional additive. The polyester composites of the present disclosure not only have ultra-high toughness, but also can maintain high tensile strength, have excellent hydrolysis resistance, can be matched with an antibacterial agent or an antistatic agent to have good antibacterial or antistatic additional functions, can be widely applied to the fields of fibers and fabrics, plastic structural parts, plastic packages or automobile interior parts, and have a wide prospect.

Abstract: Methods and apparatus for automated medical image analysis using deep learning networks are disclosed. In a method of automatically performing a medical image analysis task on a medical image of a patient, a medical image of a patient is received. The medical image is input to a trained deep neural network. An output model that provides a result of a target medical image analysis task on the input medical image is automatically estimated using the trained deep neural network. The trained deep neural network is trained in one of a discriminative adversarial network or a deep image-to-image dual inverse network.

Abstract: Methods and apparatus for automated medical image analysis using deep learning networks are disclosed. In a method of automatically performing a medical image analysis task on a medical image of a patient, a medical image of a patient is received. The medical image is input to a trained deep neural network. An output model that provides a result of a target medical image analysis task on the input medical image is automatically estimated using the trained deep neural network. The trained deep neural network is trained in one of a discriminative adversarial network or a deep image-to-image dual inverse network.

Abstract: A method and apparatus for automated liver segmentation in a 3D medical image of a patient is disclosed. A 3D medical image, such as a 3D computed tomography (CT) volume, of a patient is received. The 3D medical image of the patient is input to a trained deep image-to-image network. The trained deep image-to-image network is trained in an adversarial network together with a discriminative network that distinguishes between predicted liver segmentation masks generated by the deep image-to-image network from input training volumes and ground truth liver segmentation masks. A liver segmentation mask defining a segmented liver region in the 3D medical image of the patient is generated using the trained deep image-to-image network.

Abstract: A method and apparatus for deep learning based automatic bone removal in medical images, such as computed tomography angiography (CTA) volumes, is disclosed. Bone structures are segmented in a 3D medical image of a patient by classifying voxels of the 3D medical image as bone or non-bone voxels using a deep neural network trained for bone segmentation. A 3D visualization of non-bone structures in the 3D medical image is generated by removing voxels classified as bone voxels from a 3D visualization of the 3D medical image.

Abstract: In scan data retrieval, a mesh is fit (32) to surface data of a current patient, such as data from an optical or depth sensor (18). Meshes are also fit (48) to medical scan data, such as fitting (48) to skin surface segments of computed tomography data. The meshes or parameters derived from the meshes may be more efficiently compared (34) to identify (36) a previous patient with similar body shape and/or size. The scan configuration (38) for that patient, or that patient as altered to account for differences from the current patient, is used. In some embodiments, the parameter vector used for searching (34) includes principle component analysis coefficients. In further embodiments, the principle component analysis coefficients may be projected to a more discriminative space using metric learning.