Abstract: A method, system and computer-readable storage medium for performing a counterfactual generation operation. The counterfactual generation operation includes: receiving a subject data point; classifying the data point via a trained classifier, the classifying providing a classified data point; identifying a counterfactual using the classified data point, the counterfactual comprising another datapoint, the another data point being close to the subject data point, the another data point resulting in production of a different outcome when provided to a model when compared to an outcome resulting from the subject data point being provided to the model; and, providing the counterfactual to a destination.

Abstract: Various examples related to real time detection with recurrent networks are presented. These can be utilized in automatic insect recognition to provide accurate and rapid in situ identification. In one example, among others, a method includes training parameters of a kernel adaptive autoregressive-moving average (KAARMA) using a signal of an input space. The signal can include source information in its time varying structure. A surrogate embodiment of the trained KAARMA can be determined based upon clustering or digitizing of the input space, binarization of the trained KAARMA state and a transition table using the outputs of the trained KAARMA for each input in the training set. A recurrent network detector can then be implemented in processing circuitry (e.g., flip-flops, FPGA, ASIC, or dedicated VLSI) based upon the surrogate embodiment of the KAARMA The recurrent network detector can be configured to identify a signal class.

Abstract: An apparatus, method, and a computer readable medium for attenuating visual artifacts in processed images. An annotated dataset of images to be processed by an image processing system is created. An adversarial control network is trained to operate as an image quality expert in classifying images. After the adversarial control network has been trained, the adversarial control network is used to supervise the image processing system on-the-fly.

Abstract: Human or object presence in or absence from a field-of-view of a camera can be achieved by analyzing camera data using a processor inside of or adjacent to the camera itself. In an example, a video signal processing system receives image data from one or more cameras and uses a processing circuit to determine whether a designated object is or is not present at a particular time, during a particular interval, or over a designated sequence of frames. In an example, the designated object can include one or more of a human being, a vehicle, or a parcel. In an example, results of the determination, such as including positive human or object identification, can be used as a trigger for operation of a barrier or access door.

Abstract: Systems and methods for domain adaptation for structured output via disentangled representations are provided. The system receives a ground truth of a source domain. The ground truth is used in a task loss function for a first convolutional neural network that predicts at least one output based on inputs from the source domain and a target domain. The system clusters the ground truth of the source domain into a predetermined number of clusters, and predicts, via a second convolutional neural network, a structure of label patches. The structure includes an assignment of each of the at least one output of the first convolutional neural network to the predetermined number of clusters. A cluster loss is computed for the predicted structure of label patches, and an adversarial loss function is applied to the predicted structure of label patches to align the source domain and the target domain on a structural level.

Abstract: A system and method for a guided inspection of an apartment, home or other physical space is disclosed. The system and method use augmented reality to guide a user through a physical space. The system and method further use machine learning to automatically detect and classify damage to various physical structures in the physical space. In response to detected damage, the system may prompt a user to move closer to the detected damage for further inspection. The system can also detect obscured structures and prompt a user to make changes to the environment to increase the visibility of the obscured structures.

Abstract: An image processing device and an image processing method are provided. The image processing device comprises a receiving module, a interface conversion module, a selecting module, and a controller. The receiving module is configured to receive image signals. The interface conversion module is configured to convert the image signals into converted image signals with a target image interface. The selecting module is configured to generate at least two selected image signals from the converted image signals according to the first selecting signal. The controller is configured to provide the first selecting signal to selecting module. The image processing device generates the composite image by overlaying the at least two selected image signals.

Abstract: A high-throughput virtual drug screening system based on molecular fingerprints and deep learning, includes a deep-learning model online-modeling subsystem and an online virtual-screening subsystem. The system combines the molecular fingerprints and a deep neural network method to construct a high-throughput virtual drug screening system. The system includes built-in structural-diversity screening libraries and realizes the online automatic construction of deep learning models and virtual screening. The system helps researchers in the drug discovery industry such as medicinal chemistry to conduct rapid screening through their desired targets to obtain potential active compounds and accelerate drug discovery.

Abstract: Introduced here are health management platforms able to monitor changes in the health state of a subject based on the context of digital activities performed by, or involving, the subject. Initially, a health management platform can identify a physiological response by examining physiological data associated with a subject. Then, the health management platform can identify a stimulus presented by an electronic device that provoked the physiological response by examining contextual data associated with the subject. The contextual data may be in the form of a screenshot of a computer program in use by the subject during the physiological response. In some embodiments, the health management platform prompts the subject to specify whether the physiological response is a positive physiological response that resulted in an upward shift in health or a negative physiological response that resulted in a downward shift in health.

Abstract: A laundry data analysis apparatus based on artificial intelligence according to an embodiment of the present invention includes: a communication unit configured to receive an image including laundry data related to characteristics of laundry from an image acquisition device corresponding to a group including at least one member; and a processor configured to recognize the laundry data from the received image, acquire additional data related to the characteristics of the laundry on the basis of the recognized laundry data, store laundry information including the laundry data and the additional data into a database, and acquire member characteristic information of each of the at least one member from a plurality of laundry information corresponding to the group stored in the database.

Abstract: Methods and systems for training a machine learning model include training a machine learning model using training data. A status of the machine learning model's training is determined based on an accuracy curve of the machine learning model over the course of the training. Parameters of the training are adjusted based on the status. Training of the machine learning model is completed using the adjusted parameters.

Abstract: Methods and systems for training a computer-based classification model for classifying data are presented. The computer-based classification model is configured to classify data into one of a plurality of classifications. An initial training data set for training the classification model is obtained. In some embodiments, the training data within the initial training data set is grouped into multiple clusters, and training data within one or more clusters having corresponding ratio between a first classification and a second classification below a threshold ratio is removed from the initial training data set to generate the modified training data set. The modified training data set, instead of the initial training data set, is used to train the classification model.

Abstract: Manipulating images using computationally expensive machine learning schemes can be implemented using server-generated models of the machine learning schemes that are transmitted to a client device for application. The schemes can include convolutional neural networks having a kernel comprising a plurality of low-rank matrices.

Abstract: A channel selection method and a transmit end are provided. The method includes: ranking multiple channels, and generating a backoff count value; sequentially decrementing, from an initial timeslot, the backoff count value in each timeslot according to a ranking sequence of the channels and busy/idle states of all the channels until the backoff count value is 0; and selecting, from the multiple channels according to a result of the decrement performed on the backoff count value and a busy/idle state of at least one of the multiple channels, a channel that is used by the transmit end for sending data. The method and the transmit end can improve channel utilization.

Abstract: An advanced driver assist system (ADAS) includes a processing circuit and a memory storing instructions executable by the processing circuit. The processing circuit executes the instructions to cause the ADAS to: obtain, from a vehicle, a video sequence including a plurality of frames captured while driving the vehicle, where each of the frames corresponds to a stereo image including a first viewpoint image and a second viewpoint image; determine depth information in the stereo image based on reflected signals received while driving the vehicle; fuse the stereo image and the depth information to generated fused information, and detect at least one object included in the stereo image based on the fused information.

Abstract: A mechanism is described for facilitating embedding of human labeler influences in machine learning interfaces in computing environments, according to one embodiment. A method of embodiments, as described herein, includes detecting sensor data via one or more sensors of a computing device, and accessing human labeler data at one or more databases coupled to the computing device. The method may further include evaluating relevance between the sensor data and the human labeler data, where the relevance identifies meaning of the sensor data based on human behavior corresponding to the human labeler data, and associating, based on the relevance, human labeler data with the sensor data to classify the sensor data as labeled data.

Abstract: Techniques are disclosed for determining a location of an object based at least in part on a motion of the object. The techniques include generating a motion profile based at least in part on motion data received from a mobile device that is associated with the object. The techniques further include receiving, from a camera at a location, a plurality of images that identifies a candidate motion of a candidate object through at least a portion of the location. The techniques further include generating a candidate motion profile corresponding to the candidate motion of the candidate object based at least in part on the plurality of images. Based at least in part on a score generated by comparing the motion profile with the candidate motion profile, the techniques may determine that the candidate object is the object.

Abstract: A method and apparatus for building an image model, where the apparatus generates a target image model that includes layers duplicated from a layers of a reference image model and an additional layer, and trains the additional layer.

Abstract: Systems for sorting seeds are disclosed, as well as batches of seeds that have been sorted using the systems.

Abstract: An approach is provided for fully-automated learning to match heterogeneous feature spaces for mapping. The approach involves determining a first feature space comprising first features and a second feature space comprising second features, and classified by a feature detector into a first attribution category and a second attribution category, respectively. The approach further involves calculating a first similarity score for the first feature space based on a first distance metric applied to the first features, and a second similarity score for the second feature space based on a second distance metric applied to the second features. The approach also involves determining a transformation space comprising a first weight to be applied to the first similarity score and a second weight to be applied to the second similarity score based on matching the first attribution category and the second attribution category.