Abstract: A computer-implemented method for explaining an image classifier, the method comprising: receiving an initial image, the initial image having been wrongly classified by the image classifier; receiving an initial gradient of a function executed by the image classifier generated while classifying the initial image, the function being indicative of a probability for the initial image to belong to an initial class; converting the initial image into a latent vector, the latent vector being a representation of the initial image in a latent space; generating a plurality of perturbation vectors using the initial gradient of the function executed by the image classifier; combining the latent vector with each one of the plurality of perturbation vectors, thereby obtaining a plurality of modified vectors; for each one of the plurality of modified vectors, reconstructing a respective image, thereby obtaining a plurality of reconstructed images; transmitting the reconstructed images to the image classifier; for each one o

Abstract: Systems and methods relating to multitask transfer learning. Neural networks are used to accomplish a number of tasks and the results of these tasks are used to determine parameters common to these and other tasks. These parameters can then be used to accomplish other related tasks. In the description, data fitting as well as image related tasks are used. Task conditioning as well as the use of a KL regularizer have greatly improved results when testing the methods of the invention.

Abstract: Persistent storage may contain typed data of a plurality of types, directional relationships between pairs of the plurality of types, and a conditional dependency structure for the typed data. One or more processors may be configured to: generate an essential graph from the conditional dependency structure; orient the edges of the essential graph such that they are directed in accordance with the directional relationships; generate typed directed acyclic graphs (DAGs) that can be found in the essential graph; form a t-essential graph from a union of the typed DAGs; identify an event represented as a first vertex in the t-essential graph, wherein the first vertex is of a first type; trace backward from the first vertex and through the t-essential graph to identify a second vertex of a second type; and provide a representation of the second vertex as a cause of the event.

Abstract: A computer-implemented method for explaining an image classifier, the method comprising: receiving an initial image, the initial image having been wrongly classified by the image classifier; receiving an initial gradient of a function executed by the image classifier generated while classifying the initial image, the function being indicative of a probability for the initial image to belong to an initial class; converting the initial image into a latent vector, the latent vector being a representation of the initial image in a latent space; generating a plurality of perturbation vectors using the initial gradient of the function executed by the image classifier; combining the latent vector with each one of the plurality of perturbation vectors, thereby obtaining a plurality of modified vectors; for each one of the plurality of modified vectors, reconstructing a respective image, thereby obtaining a plurality of reconstructed images; transmitting the reconstructed images to the image classifier; for each one o

Abstract: Systems and methods relating to machine learning by using a sample data set to learn a specific task and using that learned task on a query data set. In an image classification implementation, a sample set is used to derive a task representation and the task representation is used with a task embedding network to determine parameters to be used with a neural network to perform the task. Once the parameters have been derived, the sample set and the query set are passed through neural network with the parameters. The results are then compared for similarities.

Abstract: Systems and methods relating to multitask transfer learning. Neural networks are used to accomplish a number of tasks and the results of these tasks are used to determine parameters common to these and other tasks. These parameters can then be used to accomplish other related tasks. In the description, data fitting as well as image related tasks are used. Task conditioning as well as the use of a KL regularizer have greatly improved results when testing the methods of the invention.