The technology disclosed directly operates on sequencing data and derives its own feature filters. It processes a plurality of aligned reads that span a target base position. It combines elegant encoding of the reads with a lightweight analysis to produce good recall and precision using lightweight hardware. For instance, one million training examples of target base variant sites with 50 to 100 reads each can be trained on a single GPU card in less than 10 hours with good recall and precision. A single GPU card is desirable because it a computer with a single GPU is inexpensive, almost universally within reach for users looking at genetic data. It is readily available on could-based platforms.

The technology disclosed directly operates on sequencing data and derives its own feature filters. It processes a plurality of aligned reads that span a target base position. It combines elegant encoding of the reads with a lightweight analysis to produce good recall and precision using lightweight hardware. For instance, one million training examples of target base variant sites with 50 to 100 reads each can be trained on a single GPU card in less than 10 hours with good recall and precision. A single GPU card is desirable because it a computer with a single GPU is inexpensive, almost universally within reach for users looking at genetic data. It is readily available on could-based platforms.

A method is disclosed for evaluating a classifier used to determine a traffic light signal state in images. The method includes, by a computer vision system of a vehicle, receiving at least one image of a traffic signal device of an imminent intersection. The traffic signal device includes a traffic signal face including one or more traffic signal elements. The method includes classifying, by a traffic light classifier (TLC), a classification state of the traffic signal face using labeled images correlated to the received at least one image. The classification state controls an operation of the vehicle at the intersection. The method includes evaluating a performance of the classifying of the classification state generated by the TLC. The evaluation is a label-free performance evaluation based on unlabeled images. The method includes training the TLC based on the evaluated performance.

A method is disclosed for evaluating a classifier used to determine a traffic light signal state in images. The method includes, by a computer vision system of a vehicle, receiving at least one image of a traffic signal device of an imminent intersection. The traffic signal device includes a traffic signal face including one or more traffic signal elements. The method includes classifying, by a traffic light classifier (TLC), a classification state of the traffic signal face using labeled images correlated to the received at least one image. The classification state controls an operation of the vehicle at the intersection. The method includes evaluating a performance of the classifying of the classification state generated by the TLC. The evaluation is a label-free performance evaluation based on unlabeled images. The method includes training the TLC based on the evaluated performance.

Disclosed herein is a system for watermarking a neural network, comprising memory; and at least one processor in communication with the memory; wherein the memory stores instructions for causing the at least one processor to carry out a method comprising: generating a trigger set by obtaining examples from a training set by random sampling from the training set, respective examples being associated with respective true classes of a plurality of classes; generating a set of adversarial examples by structured perturbation of the examples; generating, for each adversarial example, one or more adversarial class labels by passing the adversarial example to the neural network; and applying one or more trigger labels to each said adversarial example, wherein the one or more trigger labels are selected randomly from the plurality of classes, and wherein each trigger label is not a said true class label for the corresponding example or a said adversarial class label for the corresponding adversarial example; and storing the adversarial examples and corresponding trigger labels as the trigger set; and performing a tuning process to adjust parameters at each layer of the neural network using the trigger set, to thereby generate a watermarked neural network.

A method for receiving a full training data set including a plurality of individual training data set, dividing the plurality of individual training sets into N classes, where N is an integer greater than three, dividing the N classes into M full data classes and N-M partial data classes, performing training to obtain a trained fixed size machine learning (ML) classification model and a trained in-class confidence model, outputting a first set of prediction value(s) based on the performance of training, distributing each class of the N classes of individual training data sets to a different node of a distributed machine learning system; and outputting, from the nodes of the distributed machine learning system, a second set of prediction value(s) for each class of the N classes.

A system for sorting seeds based on their resistance to a stress is disclosed. Batches of purified seeds sorted using the system are also disclosed.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for accounting for long-tail training data.

The current disclosure provides methods and systems for visualizing, comparing, and navigating through, labeled image sequences. In one example, a degree of variation between a plurality of labels for an image in a sequence of images may be encoded as a comparison metric, and the comparison metric for each image may be graphed as a function of image position in the sequence of images, thereby providing a contextually rich view of label variation as a function of progression through the sequence of images. Further, the encoded variation of image labels may be used to automatically flag inconsistently labeled images, wherein the flagged images may be highlighted in a graphical user interface presented to a user, pruned from a training dataset, or a loss associated with the flagged image may be scaled based on the encoded variation during training of a machine learning model.

A diagnosis support apparatus performs identification for a plurality of support items, which are identification classifications about diagnosis support, and the diagnosis support apparatus is provided with a processor. The processor performs analysis processing for acquiring analysis results including an analysis result about an observation mode by analyzing at least one of an input signal specifying the observation mode and an observation image obtained by observing an inside of a subject with an endoscope; performs support item setting processing for setting a support item corresponding to the analysis results obtained by the analysis processing, among the plurality of support items, which are the identification classifications; and generates diagnosis support information, which is information used for diagnosis of a legion candidate area included in the observation image, based on an identification index corresponding to the set support item and the observation image.