Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to a path finding system for AI model optimization. The computer-implemented system can comprise a memory that can store computer-executable components. The computer-implemented system can further comprise a processor that can execute the computer-executable components stored in the memory, wherein the computer-executable components can comprise a graph generation component that can convert an AI model optimization workflow into a path finding graph comprising a plurality of paths that can capture respective relationships between a plurality of optimization tools, wherein the path finding graph can be employed to solve a graph traversal problem for an AI model optimization task based on a model optimization sequence.

Abstract: In various embodiments, a system can: access a failure image on which a first model has inaccurately performed an inferencing task; train, on a set of dummy images, a second model to learn a visual variety of the failure image, based on a loss function having a first term and a second term, the first term quantifying visual content dissimilarities between the set of dummy images and outputs predicted during training by the second model, and the second term quantifying, at a plurality of different image scales, visual variety dissimilarities between the failure image and the outputs predicted during training by the second model; and execute the second model on each of a set of training images on which the first model was trained, thereby yielding a set of first converted training images that exhibit the visual variety of the failure image.

Abstract: Techniques are described for multi-task neural network model design using task crystallization are described. In one example a task crystallization method comprises adding one or more task-specific channels to a backbone neural network adapted to perform a primary inferencing task to generate a multi-task neural network model, wherein the adding comprises adding task-specific elements to different layers of the backbone neural network for each channel of the one or more task-specific channels. The method further comprises training, by the system, the one or more task-specific channels to perform one or more additional inferencing tasks that are respectively different from one another and the primary inferencing task, comprising separately tuning and crystallizing the task-specific elements of each channel of the one or more task-specific channels.

Abstract: Systems/techniques that facilitate improved deep learning image processing are provided. In various embodiments, a system can access a medical image, wherein pixels or voxels of the medical image can be allocated among a plurality of regions. In various aspects, the system can generate, via execution of a deep learning neural network on the medical image, a set of region-wise parameter maps, wherein a region-wise parameter map can consist of one predicted parameter per region of the medical image. In various instances, the system can generate a transformed version of the medical image by feeding the set of region-wise parameter maps to an analytical transformation function. In various cases, the system can render the transformed version of the medical image on an electronic display. In various aspects, the plurality of regions can be irregular or tissue-based.

Abstract: Systems/techniques that facilitate deep learning image analysis with increased modularity and reduced footprint are provided. In various embodiments, a system can access medical imaging data. In various aspects, the system can perform, via execution of a deep learning neural network, a plurality of inferencing tasks on the medical imaging data. In various instances, the deep learning neural network can comprise a common backbone in parallel with a plurality of task-specific backbones. In various cases, the plurality of task-specific backbones can respectively correspond to the plurality of inferencing tasks.

Abstract: Techniques regarding autonomous data augmentation are provided. For example, one or more embodiments described herein can regard a system comprising a memory that can store computer-executable components. The system can also comprise a processor, operably coupled to the memory, that executes the computer-executable components stored in the memory. The computer-executable components can include a data augmentation component that executes a random unidimensional augmentation algorithm to augment a dataset for training a machine learning model via a plurality of augmentation operations. The random unidimensional augmentation algorithm can employ a global augmentation parameter that defines: a distortion magnitude associated with the plurality of augmentation operations, and a number of augmentation operations included in the plurality of augmentation operations.

Abstract: 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.