Disclosed are a multi-task training technique and resulting model for detecting distracted driving. In one embodiment, a method is disclosed comprising inputting a plurality of labeled examples into a multi-task network, the multi-task network comprising: a backbone network, the backbone network generating one or more feature vectors corresponding to each of the labeled examples, and a plurality of prediction heads coupled to the backbone network; minimizing a joint loss based on outputs of the plurality of prediction heads, the minimizing the joint loss causing a change in parameters of the backbone network; and storing a distraction classification model after minimizing the joint loss, the distraction classification model comprising the parameters of the backbone network and parameters of at least one of the prediction heads.

Included are: a simulation data acquiring unit to acquire simulation sensor data and acquire simulation traveling data; a feature amount calculating unit to calculate a feature amount from the simulation sensor data; a hyperparameter evaluation unit to evaluate whether or not a hyperparameter is a determined hyperparameter by comparing the simulation traveling data with ideal traveling data; a hyperparameter determination control unit to reset the hyperparameter until the hyperparameter evaluation unit evaluates that the hyperparameter is the determined hyperparameter, and repeatedly operate a mobile object simulator; and a teacher data generating unit to generate teacher data in which the hyperparameter evaluated as the determined hyperparameter by the hyperparameter evaluation unit and the feature amount calculated by the feature amount calculating unit are paired.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for characterizing activity in a recurrent artificial neural network. In one aspect, a method for identifying decision moments in a recurrent artificial neural network includes determining a complexity of patterns of activity in the recurrent artificial neural network, wherein the activity is responsive to input into the recurrent artificial neural network, determining a timing of activity having a complexity that is distinguishable from other activity that is responsive to the input, and identifying the decision moment based on the timing of the activity that has the distinguishable complexity.

In a variety of embodiments, machine classifiers may model multi-turn dialogue as a one-to-many prediction task. The machine classifier may be trained using adversarial bootstrapping between a generator and a discriminator with multi-turn capabilities. The machine classifiers may be trained in both auto-regressive and traditional teacher-forcing modes, with the generator including a hierarchical recurrent encoder-decoder network and the discriminator including a bi-directional recurrent neural network. The discriminator input may include a mixture of ground truth labels, the teacher-forcing outputs of the generator, and/or noise data. This mixture of input data may allow for richer feedback on the autoregressive outputs of the generator. The outputs can be ranked based on the discriminator feedback and a response selected from the ranked outputs.

Systems and methods for training a model are described herein. In one example, a system for training the model includes a processor and a memory in communication with the processor having a training module. The training module has instructions that cause the processor to determine a contrastive loss using a self-supervised contrastive loss function, adjust, based on the contrastive loss, model weights a visual backbone that generated feature maps and/or a textual backbone that generated feature vectors. The training module also has instructions that cause the processor to determine a localized loss using a supervised loss function that compares an image-caption attention map with visual identifiers and adjust, based on the localized loss, the model weights the visual backbone and/or the textual backbone.

Systems, apparatus, interfaces, methods, and articles of manufacture that provide for Artificial Intelligence (AI) User Interface (UI) and/or Graphical User Interface (GUI) generation.

The present disclosure relates to systems, methods, and computer readable media that evaluate performance of a machine learning system in connection with a test dataset. For example, systems disclosed herein may receive a test dataset and identify label information for the test dataset including feature information and ground truth data. The systems disclosed herein can compare the ground truth data and outputs generated by a machine learning system to evaluate performance of the machine learning system with respect to the test dataset. The systems disclosed herein may further generate feature clusters based on failed outputs and corresponding features and generate a number of performance views that illustrate performance of the machine learning system with respect to clustered groupings of the test dataset.

Provided is a process of modeling methods organized in racks of a machine learning pipeline to facilitate optimization of performance using modelling methods for implementation of machine learning design in an object-oriented modeling (OOM) framework, the process including: writing classes using object-oriented modelling of optimization methods, modelling methods, and modelling racks; writing parameters and hyper-parameters of the modeling methods as attributes as the modeling methods; scanning modelling racks classes to determine first class definition information; selecting a collection of rack and selecting modeling method objects; scanning modelling method classes to determine second class definition information; assigning racks and locations within the racks to modeling method objects; and invoking the class definition information to produce object manipulation functions that allow access the methods and attributes of at least some of the modeling method objects, the manipulation functions being configured to effectuate writing locations within racks and attributes of racks.

An estimation unit inputs learning data to a lightweight model for outputting an estimation result in accordance with data input and acquires a first estimation result. Further, the updating unit updates a parameter of the lightweight model so that a model cascade including the lightweight model and a high-accuracy model is optimized in accordance with the first estimation result and a second estimation result obtained by inputting the learning data to the high-accuracy model, which is a model for outputting an estimation result in accordance with input data and has a lower processing speed than the first model or a higher estimation accuracy than the lightweight model.

The present subject matter describes a method for labeling data in a computing system based on artificial intelligent techniques. The method comprises receiving input data and ordering the received input-data in a plurality of classes inferred based on at-least one of clustering and anomaly detection. The method further comprises receiving one more manual annotated labels for the ordered data. A first machine-learning (ML) model is trained with respect to the ordered data and thereby generating new labels. The performance of the first ML model is computed based on a comparison between the manual labels and the new labels. The labels are automatically propagated to unlabelled-portion of the ordered data based on execution of the first ML model based on accuracy of first ML model being above a predefined threshold.