A method and system for generating neural architectures to perform a particular task. An actor neural network, as part of a continuous action reinforcement learning (RL) agent, generates a randomized continuous actions parameters to encourage exploration of a search space to generate candidate architectures without bias. The continuous action parameters are discretized and applied to a search space to generate candidate architectures, the performance of which for performing the particular task is evaluated. Corresponding reward and state are determined based on the performance. A critic neural network, as part of the continuous action RL agent, learns a mapping of the continuous action to a reward using modified Deep Deterministic Policy Gradient (DDPG) with quantile loss function by sampling a list of top performing architectures. The actor neural network is updated with the learned mapping.

There is disclosed a method of and a system for predicting text in an image using one or more constraints. The image is input to a machine learning algorithm (MLA). The MLA outputs a probability distribution. The probability distribution comprises a predicted probability for each of a plurality of pairs, where each pair comprises a class and a next state of the MLA. The states of the probability distribution are added to a set of states to be searched. States that are end states or that fail to satisfy at least one of the constraints are removed from the set of states to be searched. States of the set of states to be searched are input to the MLA. The search is repeated with new states output by the MLA. End states output by the MLA are output as output states that each comprise a sequence of characters.

Provided are an item identification method and apparatus, a device, and a computer-readable storage medium. The method includes: categories of items contained in a group of to-be-identified items and quantity information of items in each category contained in the group of to-be-identified items are determined by performing short-range wireless communication with each item in a group of to-be-identified items in a scenario region, each item containing a short-range wireless communication tag corresponding to a category of each item; acquired images of the group of to-be-identified items are identified to obtain an image identification result of the group of to-be-identified items, the image identification result including a category identification result of each item in the group of to-be-identified items; and an item identification result of the group of to-be-identified items is determined based on the quantity information and the image identification result.

At compile-time, a processor develops a computer program by receiving an input that includes multiple nodes and connections between pairs of the nodes. The nodes represent object properties such as properties of objects that an autonomous vehicle (AV) detects while moving about an environment. For each node, the system will identify a depth that represents a number of nodes along a longest path from that node to any available input node. The system will order the nodes by depth in a sequence, and it will build a graph-based program specification that includes the nodes in the sequence, along with the connections. The graph-based program specification may correspond to a directed acyclic graph (DAG). The system will compile the graph-based program specification into a computer-readable program, and it will save the computer-readable program to a memory so that the AV or other system can use it at run-time.

Techniques are described for automated operations to determine tree inventory information for an area of land using visual data of overhead image(s), such as by using a trained prediction model specific to an ecological region to which the land area belongs as part of probabilistically determining multiple types of information about trees in that land area, and for subsequently using the determined tree inventory information in one or more manners (e.g., to improve management of trees in that land area). The images may, for example, include spectral satellite images that include at least visible light data for an area of land, and the determined tree inventory information may include information about the trees present on the land area, such as, for example, predictions of particular tree species, quantities of each of the tree species, sizes of the trees, etc.

In various examples, systems and methods are disclosed herein for dynamically updating a neural network having a plurality of kernels. The system may identify a first subset of kernels from the plurality of kernels in the neural network. The system may then determine the characteristics of each respective kernel in the first subset. The system may then compare the characteristics of the respective kernels in the first subject to a dynamic rule set. In response to the system comparing the characteristics of the respective kernels in the first subset to the dynamic rule set, the system identifies a second subset of the first subset based on the comparing, automatically generates instructions to combine the second subset of kernels, and updates the neural network based on the one or more instructions. The neural network may have a simplified compute graph based on the above dynamic updating systems and methods.

According to various embodiments, a wrinkle detection service providing server for providing a wrinkle detection method based on an artificial intelligence may include a data pre-processor for obtaining a skin image of a user from a skin measurement device and performing pre-processing based on feature points based on the skin image; a wrinkle detector for inputting the skin image pre-processed through the data pre-processing into an artificial neural network and generating a wrinkle probability map corresponding to the skin image; a data post-processor for post-processing the generated wrinkle probability map; and a wrinkle visualization service providing unit for superimposing the post-processed wrinkle probability map on the skin image and providing a wrinkle visualization image to a user terminal of the user.

According to various embodiments, a wrinkle detection service providing server for providing a wrinkle detection method based on an artificial intelligence may include a data pre-processor for obtaining a skin image of a user from a skin measurement device and performing pre-processing based on feature points based on the skin image; a wrinkle detector for inputting the skin image pre-processed through the data pre-processing into an artificial neural network and generating a wrinkle probability map corresponding to the skin image; a data post-processor for post-processing the generated wrinkle probability map; and a wrinkle visualization service providing unit for superimposing the post-processed wrinkle probability map on the skin image and providing a wrinkle visualization image to a user terminal of the user.

One embodiment facilitates recognizing parts of a vehicle. A convolution module is configured to generate a convolution feature map of a vehicle image. A region proposal module is configured to determine, based on the convolution feature map, one or more proposed regions, wherein a respective proposed region corresponds to a target of a respective vehicle part. A classification module is configured to determine a class and a bounding box of a vehicle part corresponding to a proposed region based on a feature of the proposed region. A conditional random field module is configured to optimize classes and bounding boxes of the vehicle parts based on correlated features of the corresponding proposed regions. A reporting module is configured to generate a result which indicates a list including an insurance claim item and corresponding damages based on the optimized classes and bounding boxes of the vehicle parts.

Certain aspects of the present disclosure are directed to methods and apparatus for predicting subject motion using probabilistic models. One example method generally includes receiving training data comprising a set of subject pose trees. The set of subject pose trees comprises a plurality of subsets of subject pose trees associated with an image in a sequence of images, and each subject pose tree in the subset indicates a location along an axis of the image at which each of a plurality of joints of a subject is located. The received training data may be processed in a convolutional neural network to generate a trained probabilistic model for predicting joint distribution and subject motion based on density estimation. The trained probabilistic model may be deployed to a computer vision system and configured to generate a probability distribution for the location of each joint along the axis.