Abstract: Systems and methods train a transformer-based policy network and Generative Adversarial Network (GAN) by initializing a transformer-based policy network to model action sequences by encoding temporal dependencies within sensor data. Multi-head self-attention mechanisms process sequential sensor inputs by being pre-trained on a labeled dataset having sensor data from known low-risk action sequences. A generator within the GAN is trained to produce generated action sequences, which mimic behavior of low-risk action sequences. A discriminator within the GAN is concurrently trained to differentiate between action sequences derived from the labeled dataset and synthetic action sequences produced by the generator. A feedback loop is employed to adjust parameters to produce sequences indistinguishable from real low-risk action sequences.

Abstract: Systems and methods for optimizing key performance indicators (KPIs) using adversarial imitation deep learning include processing sensor data received from sensors to remove irrelevant data based on correlation to a final KPI and generating, using a policy generator network with a transformer-based architecture, an optimal sequence of actions based on the processed sensor data. A discriminator network is employed to differentiate between the generated action sequences and real-world high performance sequences employing. Final KPI results are estimated based on the generated action sequences using a performance prediction network. The generated action sequences are applied to the process to optimize the KPI in real-time.

Abstract: Systems and methods are provided for classifying components include monitoring sensors to collect sensor data related to a state of a plurality of components; processing, by a computing system, the sensor data to generate an action sequence using a transformer-based policy network for each of the components. A risk score is generated for the action sequence using a Generative Adversarial Network (GAN), wherein the GAN includes a generator for generating action sequences and a discriminator to distinguish low-risk action sequences in accordance with a threshold. The low-risk action sequences are associated with components in the plurality of components based on the risk score. A status of the low-risk action sequences is communicated to the components.

Abstract: Systems and methods for training a time-series-language (TSLa) model adapted for domain-specific tasks. An encoder-decoder neural network can be trained to tokenize time-series data to obtain a discrete-to-language embedding space. The TSLa model can learn a linear mapping function by concatenating token embeddings from the discrete-to-language embedding space with positional encoding to obtain mixed-modality token sequences. Token augmentation can transform the tokens from the mixed-modality token sequences with to obtain augmented tokens. The augmented tokens can train the TSLa model using a computed token likelihood to predict next tokens for the mixed-modality token sequences to obtain a trained TSLa model. A domain-specific dataset can fine-tune the trained TSLa model to adapt the trained TSLa model to perform a domain-specific task.

Abstract: Methods and systems include annotating a set of training data to indicate tokens that are sensitive. Instructions are generated based on the training data, including original token sequences and respective substituted token sequences. A language model is fine-tuned using the instructions with a penalty-based loss function to generate a privacy-protected language model.

Abstract: The present application discloses a multi-spectral fundus imaging system and method using dynamic visual stimulation, where the imaging system includes: a multi-spectral light source capable of emitting multiple different wavelengths; a mid-pass mirror being a reflecting mirror with a central hole penetrating the reflecting mirror; an imaging focusing lens group; an image acquisition device; and a controller configured to control the multi-spectral light source and the image acquisition device to work synchronously; a pattern sent by the optical stimulation device is transmitted to the fundus through the image focusing lens group and the central hole of the mid-pass mirror in sequence; an imaging light reflected from the fundus passes through the central hole of the mid-pass mirror and the imaging focusing lens group in sequence; the image acquisition device acquires the image to complete a multi-spectral fundus image acquisition.

Abstract: Systems and methods for time-series forecasting via multi-modal augmentation and fusion. Time-series data and modality data can be decomposed into seasonal and trend representations with trend-seasonal decomposition. Using an encoder transformer model, time-series data embeddings and modality data embeddings can be concatenated from the seasonal representations and the trend representations to obtain crossed representations. Using the encoder transformer model, the modality data embeddings and the time-series data embeddings can be processed separately to obtain singular representations. The crossed representations and the singular representations can be augmented through joint trend-seasonal decomposition to obtain augmented seasonal data and augmented trend data. Using a decoder, augmented seasonal data and augmented trend data can be fused to obtain fused augmented data.

Abstract: An electronic device includes at least a battery, a working circuit, and a boost circuit. When the battery supplies power to the working circuit, the boost circuit supplies power to the working circuit in response to that the electronic device meets a low-temperature or low-voltage condition. In a power supply path switching process, the boost circuit first supplies power to the working circuit through a diode, and then disconnects a path for supplying power to the working circuit by the battery. Before the path for supplying power to the working circuit by the battery is disconnected, a voltage for supplying power to the working circuit by the boost circuit through the diode is controlled not to be higher than a voltage for supplying power to the working circuit by the battery.

Abstract: A computer-implemented method for multi-model representation learning is provided. The method includes encoding, by a trained time series (TS) encoder, an input TS segment into a TS-shared latent representation and a TS-private latent representation. The method further includes generating, by a trained text generator, a natural language text that explains the input TS segment, responsive to the TS-shared latent representation, the TS-private latent representation, and a text-private latent representation.

Abstract: Methods and systems for skill prediction include aggregating locally trained parameters from client systems to generate updated global parameters. Parameterized vectors from the client systems are clustered into prototype clusters. A centroid of each prototype cluster is determined and the parameterized vectors from the client systems are matched to centroids of the prototype clusters to identify sets of updated local prototype vectors. The updated global parameters and the updated local prototype vectors are distributed to the client systems.

Abstract: Methods and systems for training a healthcare treatment machine learning model include aggregating local weights from a set of clients to update a set of global weights for an imitation-based skill learning model. A set of local prototype vectors are clustered from the plurality of clients to generate clusters. Representative vectors are selected for the clusters as a set of global prototypes. Client-specific prototype vectors are determined for the clients based on the representative vectors. The updated set of global weights and the client-specific prototype vectors are distributed to the clients.

Abstract: Methods and systems for training a healthcare treatment machine learning model include segmenting a patient trajectory, which includes a sequence of patient states and treatment actions. A machine learning model is trained based on segments of the patient trajectory, including a prototype layer that learns prototype vectors representing respective classes of trajectory segments and an imitation learning layer that learns a policy to select a treatment action based on an input state and a skill embedding.

Abstract: Systems and methods for personalized federated learning. The method may include receiving at a central server local models from a plurality of clients, and aggregating a heterogeneous data distribution extracted from the local models. The method can further include processing the data distribution as a linear mixture of joint distributions to provide a global learning model, and transmitting the global learning model to the clients. The global learning model is used to update the local model.

Abstract: A method that includes: transmitting, by an electronic device, a first detecting signal when the electronic device is in a reverse wireless charging mode; receiving, by the electronic device at a gap moment between at least two adjacent moments at which the first detecting signal is transmitted, a second detecting signal transmitted by a wireless charging device; and if the second detecting signal received by the electronic device meets a preset condition, automatically switching, by the electronic device, from the reverse wireless charging mode to a forward wireless charging mode.

Abstract: Methods and systems for training a model include performing skill discovery, using a set of demonstrations that includes known-good demonstrations and noisy demonstrations, to generate a set of skills. A unidirectional skill embedding model is trained in a first training while parameters of a skill matching model and low-level policies that relate skills to actions are held constant. The unidirectional skill embedding model, the skill matching model, and the low-level policies are trained together in an end-to-end fashion in a second training.

Abstract: A computer-implemented method for employing a time-series-to-text generation model to generate accurate description texts is provided. The method includes passing time series data through a time series encoder and a multilayer perceptron (MLP) classifier to obtain predicted concept labels, converting the predicted concept labels, by a serializer, to a text token sequence by concatenating an aspect term and an option term of every aspect, inputting the text token sequence into a pretrained language model including a bidirectional encoder and an autoregressive decoder, and using adapter layers to fine-tune the pretrained language model to generate description texts.

Abstract: A method for learning a self-explainable imitator by discovering causal relationships between states and actions is presented. The method includes obtaining, via an acquisition component, demonstrations of a target task from experts for training a model to generate a learned policy, training the model, via a learning component, the learning component computing actions to be taken with respect to states, generating, via a dynamic causal discovery component, dynamic causal graphs for each environment state, encoding, via a causal encoding component, discovered causal relationships by updating state variable embeddings, and outputting, via an output component, the learned policy including trajectories similar to the demonstrations from the experts.

Abstract: A method for acquiring skills through imitation learning by employing a meta imitation learning framework with structured skill discovery (MILD) is presented. The method includes learning behaviors or tasks, by an agent, from demonstrations: by learning to decompose the demonstrations into segments, via a segmentation component, the segments corresponding to skills that are transferrable across different tasks, learning relationships between the skills that are transferrable across the different tasks, employing, via a graph generator, a graph neural network for learning implicit structures of the skills from the demonstrations to define structured skills, and generating policies from the structured skills to allow the agent to acquire the structured skills for application to one or more target tasks.

Abstract: A method for learning a self-explainable imitator by discovering causal relationships between states and actions is presented. The method includes obtaining, via an acquisition component, demonstrations of a target task from experts for training a model to generate a learned policy, training the model, via a learning component, the learning component computing actions to be taken with respect to states, generating, via a dynamic causal discovery component, dynamic causal graphs for each environment state, encoding, via a causal encoding component, discovered causal relationships by updating state variable embeddings, and outputting, via an output component, the learned policy including trajectories similar to the demonstrations from the experts.

Abstract: A method for acquiring skills through imitation learning by employing a meta imitation learning framework with structured skill discovery (MILD) is presented. The method includes learning behaviors or tasks, by an agent, from demonstrations: by learning to decompose the demonstrations into segments, via a segmentation component, the segments corresponding to skills that are transferrable across different tasks, learning relationships between the skills that are transferrable across the different tasks, employing, via a graph generator, a graph neural network for learning implicit structures of the skills from the demonstrations to define structured skills, and generating policies from the structured skills to allow the agent to acquire the structured skills for application to one or more target tasks.