A neural network in multi-task deep learning paradigm for machine vision includes an encoder that further includes a first, a second, and a third tier. The first tier comprises a first-tier unit having one or more first-unit blocks. The second tier receives a first-tier output from the first tier at one or more second-tier units in the second tier, a second-tier unit comprises one or more second-tier blocks, the third tier receives a second-tier output from the second tier at one or more third-tier units in the third tier, and a third-tier block comprises one or more third-tier blocks. The neural network further comprises a decoder operatively the encoder to receive an encoder output from the encoder as well as one or more loss function layers that are configured to backpropagate one or more losses for training at least the encoder of the neural network in a deep learning paradigm.

Systems, methods, and computer program products leverage artificial intelligence, and machine learning to process image enhancements using image enhancement techniques and algorithms. Image enhancements are determined to be best suited for enhancing each image as a function of each images' calculated validation parameters by an analytics engine. The images are each categorized by the image quality as a function of the validation parameters. Images identified as having an improvement space are further processed by querying the images' validation parameters using a knowledge base comprising historical data describing past image enhancements and historical validation parameters to the current image. A matrix of recommended enhancements, along with a predicted success rate for improving the image quality is provided to a user interface. A user can select one or more enhancements to apply to the image(s) and further provide feedback to the knowledge base, further improving enhancement recommendations and success rates.

Systems and methods for improving the accuracy of a computer system for object identification/classification through the use of weakly supervised learning are provided herein. In some embodiments, the method includes (a) receiving at least one set of curated data, wherein the curated data includes labeled images, (b) using the curated data to train a deep network model for identifying objects within images, wherein the trained deep network model has a first accuracy level for identifying objects, receiving a first target accuracy level for object identification of the deep network model, determining, automatically via the computer system, an amount of weakly labeled data needed to train the deep network model to achieve the first target accuracy level, and augmenting the deep network model using weakly supervised learning and the weakly labeled data to achieve the first target accuracy level for object identification by the deep network model.

A reinforcement learning method for frame-level bit allocation is disclosed. The reinforcement learning method includes steps of: (a) at a testing time, computing a state according to a plurality of features; (b) determining an action according to a policy; (c) determining a number of bits allocated to an i-th frame in a group of pictures (GOP) according to the action, a GOP-level bit budget and the state, wherein i is a positive integer; (d) encoding the i-th frame according to the number of bits allocated to the i-th frame in the GOP; and (e) repeating the steps (a)(d) until an end of the GOP.

Intent determination based on one or more multi-model structures can include generating an output from each of a plurality of domain-specific models in response to a received input. The domain-specific models can comprise simultaneously trained machine learning models that are trained using a corresponding local loss metric for each domain-specific model and a global loss metric for the plurality of domain-specific models. The presence or absence of an intent corresponding to one or more domain-specific models can be determined by classifying the output of each domain-specific model.

An artificial intelligence platform and associated methods of training and use are disclosed. An example apparatus includes a data pipeline to: preprocess data using one or more preprocessing operations applied to features associated with the data; and enable debugging to visualize the preprocessed data. The example apparatus includes a network to: instantiate one or more differentiable operations in a training configuration to train an artificial intelligence model; capture feedback including optimization and loss information to adjust the training configuration; and store one or more metrics to evaluate performance of the artificial intelligence model. The example apparatus includes an estimator to: store the training configuration for the artificial intelligence model; configure the pipeline and the network based on the training configuration; iteratively link the pipeline and the network based on the training configuration; and initiate training of the artificial intelligence model using the linked pipeline and network.

The technology disclosed assigns quality scores to bases called by a neural network-based base caller by (i) quantizing classification scores of predicted base calls produced by the neural network-based base caller in response to processing training data during training, (ii) selecting a set of quantized classification scores, (iii) for each quantized classification score in the set, determining a base calling error rate by comparing its predicted base calls to corresponding ground truth base calls, (iv) determining a fit between the quantized classification scores and their base calling error rates, and (v) correlating the quality scores to the quantized classification scores based on the fit.

In an aspect, an artificial intelligence advisory system for vibrant constitutional guidance, the system comprising a computing device; an advisory module operating on the computing device, wherein the advisory module is configured to receive at least a user input from a user client device; evaluate the content of the user input to identify a theme of conversation; locate an advisor client device operated by an informed advisor utilizing the identified theme of conversation; and an artificial intelligence advisor operating on the computing device, wherein the artificial intelligence advisor is configured to match the theme of conversation to a repository response utilizing a first machine-learning process, wherein the repository response contains a plurality of textual outputs related to the theme of conversation; select a textual output contained within the repository response; and transmit the textual output to the user client device.

A nuclear image processing method is provided. The method includes the following steps: inputting a normalized standard space nuclear image; selecting a voxel of the normalized standard space nuclear image and collecting the values of the neighbor voxels to form a voxel value set; conducting a data augmentation algorithm to generate a voxel distribution function; calculating an expected value of the distribution and calculating a first standard deviation of the portion over the expected value and a second standard deviation of the portion lower than the expected value; repeating the above steps to calculate the expected value, the first standard deviation and the second standard deviation of the necessary voxels, so as to form an image standardization template set including expected value template, first standard deviation template and the second standard deviation template.

Techniques are provided for deep neural network (DNN) identification of realistic synthetic images generated using a generative adversarial network (GAN). According to an embodiment, a system is described that can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise, a first extraction component that extracts a subset of synthetic images classified as non-real like as opposed to real-like, wherein the subset of synthetic images were generated using a GAN model. The computer executable components can further comprise a training component that employs the subset of synthetic images and real images to train a DNN network model to classify synthetic images generated using the GAN model as either real-like or non-real like