A robot includes an umbrella portion capable of performing a rotational movement and an opening/closing movement of an umbrella; and a processor. The processor acquires emotion data representing a pseudo emotion in accordance with an external stimulus, and controls, based on the emotion data, at least one of the rotational movement or the opening/closing movement of the umbrella of the umbrella portion.

In one aspect, there is provided a method performed by one or more data processing apparatus, the method includes: obtaining a network input including a respective data element at each input position in a sequence of input positions, and processing the network input using a neural network to generate a network output that defines a prediction related to the network input, where the neural network includes a sequence of encoder blocks and a decoder block, where each encoder block has a respective set of encoder block parameters, and where the set of encoder block parameters includes multiple brain emulation parameters that, when initialized, represent biological connectivity between multiple biological neuronal elements in a brain of a biological organism.

In one aspect, there is provided a method performed by one or more data processing apparatus, the method includes: obtaining a network input including a respective data element at each input position in a sequence of input positions, and processing the network input using a neural network to generate a network output that defines a prediction related to the network input, where the neural network includes a sequence of encoder blocks and a decoder block, where each encoder block has a respective set of encoder block parameters, and where the set of encoder block parameters includes multiple brain emulation parameters that, when initialized, represent biological connectivity between multiple biological neuronal elements in a brain of a biological organism.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing defect detection using brain emulation neural networks. One of the methods includes obtaining an image of a manufactured article; processing the image of the manufactured article using an encoder subnetwork of a defect detection neural network to generate an encoder subnetwork output; processing the encoder subnetwork output using a brain emulation subnetwork of the defect detection neural network to generate a brain emulation subnetwork output, wherein the brain emulation subnetwork has an architecture that comprises brain emulation parameters that, when initialized, represent biological connectivity between biological neuronal elements in a brain of a biological organism; processing the brain emulation subnetwork output using a decoder subnetwork of the defect detection neural network to generate a network output that predicts whether the manufactured article includes a defect; and taking an action based on the network output.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing defect detection using brain emulation neural networks. One of the methods includes obtaining an image of a manufactured article; processing the image of the manufactured article using an encoder subnetwork of a defect detection neural network to generate an encoder subnetwork output; processing the encoder subnetwork output using a brain emulation subnetwork of the defect detection neural network to generate a brain emulation subnetwork output, wherein the brain emulation subnetwork has an architecture that comprises brain emulation parameters that, when initialized, represent biological connectivity between biological neuronal elements in a brain of a biological organism; processing the brain emulation subnetwork output using a decoder subnetwork of the defect detection neural network to generate a network output that predicts whether the manufactured article includes a defect; and taking an action based on the network output.

In Multi-Policy Decision-Making (MPDM), many computationally-expensive forward simulations are performed in order to predict the performance of a set of candidate policies. In risk-aware formulations of MPDM, only the worst outcomes affect the decision making process, and efficiently finding these influential outcomes becomes the core challenge. Recently, stochastic gradient optimization algorithms, using a heuristic function, were shown to be significantly superior to random sampling. In this disclosure, it was shown that accurate gradients can be computed-even through a complex forward simulation—using approaches similar to those in dep networks. The proposed approach finds influential outcomes more reliably, and is faster than earlier methods, allowing one to evaluate more policies while simultaneously eliminating the need to design an easily-differentiable heuristic function.

In Multi-Policy Decision-Making (MPDM), many computationally-expensive forward simulations are performed in order to predict the performance of a set of candidate policies. In risk-aware formulations of MPDM, only the worst outcomes affect the decision making process, and efficiently finding these influential outcomes becomes the core challenge. Recently, stochastic gradient optimization algorithms, using a heuristic function, were shown to be significantly superior to random sampling. In this disclosure, it was shown that accurate gradients can be computed-even through a complex forward simulation—using approaches similar to those in dep networks. The proposed approach finds influential outcomes more reliably, and is faster than earlier methods, allowing one to evaluate more policies while simultaneously eliminating the need to design an easily-differentiable heuristic function.

An AI apparatus includes a microphone to acquire speech data including multiple languages, and a processor to acquire text data corresponding to the speech data, determine a main language from languages included in the text data, acquire a translated text data obtained by translating a text data portion, which has a language other than the main language, in the main language, acquire a morpheme analysis result for the translated text data, extract a keyword for intention analysis from the morpheme analysis result, acquire an intention pattern matched to the keyword, and perform an operation corresponding to the intention pattern.

A communication robot includes a housing and a speaker. The communication robot performs a motion of emitting a sound including a particular phoneme. With such a configuration, it is possible to provide a new communication robot that contributes to the development of the listening ability of languages. For example, the communication robot may include a storage. The communication robot may be configured to determine a motion to be performed based on the information of the storage.

A world in which a moving body moves is analyzed by using a semantic model of the world. A space feature characterizing a space in the world is defined by an item set that at least includes attribute information of a plurality of components present in and around the space. A specific space is a space where the moving body exhibits a characteristic behavior in the world. A specific space feature is the space feature characterizing the specific space. A plurality of components present in and around the specific space in a first world is extracted, and the specific space feature is defined by the item set. Then, a similar space having the space feature similar to the specific space feature regarding the specific space in the first world is extracted from a second world.