Techniques, systems, and devices are described for providing a computational frame for estimating high-dimensional stochastic behaviors. In one exemplary aspect, a method for performing numerical estimation includes receiving a set of measurements of a stochastic behavior. The set of correlated measurements follows a non-standard probability distribution and is non-linearly correlated. Also, a non-linear relationship exists between a set of system variables that describes the stochastic behavior and a corresponding set of measurements. The method includes determining, based on the set of measurements, a numerical model of the stochastic behavior. The numerical model comprises a feature space comprising non-correlated features corresponding to the stochastic behavior. The non-correlated features have a dimensionality of M and the set of measurements has a dimensionality of N, M being smaller than N. The method includes generating a set of approximated system variables corresponding to the set of measurements based on the numerical model.

For machine training and application of a trained complex-valued machine learning model, an activation function of the machine learning model, such as a neural network, includes a learnable parameter that is complex or defined in a complex domain with two dimensions, such as real and imaginary or magnitude and phase dimensions. The complex learnable parameter is trained for any of various applications, such as MR fingerprinting, other medical imaging, or non-medical uses.

Systems and methods for automated and explainable machine learning to generate seamlessly actionable insights by generating explainable personas directly from customer relationship management systems are disclosed. The personas are defined as a collection of segments, scored by likelihood to generate good opportunities, accompanied ranked profile attribute importance, with descriptive names and summaries, associated human and database readable queries which have been generated to optimally find cluster candidates in a broader data universe. Such a system would effectively and accurately model the composition of past clients, perform the categorization in an explainable way such that actions can be taken on the information to have predictable results. What is further required are the mean to categorize small text components, trained over dependent and independent model sets, to enable a cleaner and more explicit representation of information rich short-strings, in order to facilitate a more meaningful representation of the user profiles.

According to one aspect of an embodiment a learning apparatus includes a first acquiring unit that acquires first output information that is output by an output layer when predetermined input information is input to a model that includes an input layer, a plurality of intermediate layers, and the output layer. The learning apparatus includes a second acquiring unit that acquires intermediate output information that is based on pieces of intermediate information that are output by the plurality of intermediate layers when the input information is input to the model. The learning apparatus includes a learning unit that learns the model based on the first output information and the intermediate output information.

One aspect of the disclosure relates to systems and methods for determining probabilities of successful synthesis of materials in the real world at one or more points in time. The probabilities of successful synthesis of materials in the real world at one or more points in time can be determined by representing the materials and their pre-defined relationships respectively as nodes and edges in a network form, and computation of the parameters of the nodes in the network as input to a classification model for successful synthesis. The classification model being configured to determine probabilities of successful synthesis of materials in the real world at one or more points in time.

Methods, systems, and non-transitory computer readable storage media are disclosed for analyzing feature impact of a machine-learning model using prototypes across analytical spaces. For example, the disclosed system can identify features of data points used to generate outputs via a machine-learning model and then map the features to a feature space and the outputs to a label space. The disclosed system can then utilize an iterative process to determine prototypes from the data points based on distances between the data points in the feature space and the label space. Furthermore, the disclosed system can then use the prototypes to determine the impact of the features within the machine-learning model based on locally sensitive directions; region variability; or mean, range, and variance of features of the prototypes.

The technology disclosed provides a so-called “pointer sentinel mixture architecture” for neural network sequence models that has the ability to either reproduce a token from a recent context or produce a token from a predefined vocabulary. In one implementation, a pointer sentinel-LSTM architecture achieves state of the art language modeling performance of 70.9 perplexity on the Penn Treebank dataset, while using far fewer parameters than a standard softmax LSTM.

A method for providing a speech and an intelligent computing device controlling a speech providing apparatus are disclosed. A method for providing a speech according to an embodiment of the present invention includes obtaining a message, converting the message into a speech, and determining output pattern based on a generation situation of the message, so that it is possible to more realistically convey a situation at a time of message generation to a receiver of TTS. One or more of the voice providing method, devices, intelligent computing devices controlling the voice providing device, and servers of the present invention may include artificial intelligence modules, drones (Unmanned Aerial Vehicles, UAVs), robots, Augmented Reality (AR) devices, and virtual reality (VR) devices, devices related to 5G services, and the like.

Due to the high language use variability in real-life, manual construction of semantic resources to cover all synonyms is prohibitively expensive and may result in limited coverage. Described herein are systems and methods that automate the process of synonymy resource development, including both formal entities and noisy descriptions from end-users. Embodiments of a multi-task model with hierarchical task relationship are presented that learn more representative entity/term embeddings and apply them to synonym prediction. In model embodiments, a skip-gram word embedding model is extended by introducing an auxiliary task “neighboring word/term semantic type prediction” and hierarchically organize them based on the task complexity. In one or more embodiments, existing term-term synonymous knowledge is integrated into the word embedding learning framework. Embeddings trained from the multi-task model embodiments yield significant improvement for entity semantic relatedness evaluation, neighboring word/term semantic type prediction, and synonym prediction compared with baselines.

Techniques are disclosed for identifying hypocrisy in text. A computer system creates, from fragments of text, a syntactic tree that represents syntactic relationships between words in the fragments. The system identifies, in the syntactic tree, a first entity and a second entity. The system further determines that the first entity is opposite to the second entity. The system further determines a first sentiment score for a first fragment comprising the first entity and a second sentiment score for a second fragment comprising the second entity. The system, responsive to determining that the first sentiment score and the second sentiment score indicate opposite emotions, identifies the text as comprising hypocrisy and providing the text to an external device.