International Business Machines Corporation

Rahul Aralikatte

Senthil Kumar Kumarasamy Mani

Srikanth Govindaraj Tamilselvam

Anush Sankaran

Naveen Panwar

Shreya Khare

Vijay Ekambaram

Giriprasad Sridhara

A method, computer system, and a computer program product for debugging a deep neural network is provided. The present invention may include identifying, automatically, one or more debug layers associated with a deep learning (DL) model design/code, wherein the identified one or more debug layers include one or more errors, wherein a reverse operation is introduced for the identified one or more debug layers. The present invention may then include presenting, to a user, a debug output based on at least one break condition, wherein in response to determining the at least one break condition is satisfied, triggering the debug output to be presented to the user, wherein the presented debug output includes a fix for the identified one or more debug layers in the DL model design/code and at least one actionable insight.

Debugging deep neural networks

One embodiment provides a method, including: mining a plurality of deep-learning models from a plurality of input sources; extracting information from each of the deep-learning models, by parsing at least one of (i) code corresponding to the deep-learning model and (ii) text corresponding to the deep-learning model; identifying, for each of the deep-learning models, operators that perform operations within the deep-learning model; producing, for each of the deep-learning models and from (i) the extracted information and (ii) the identified operators, an ontology comprising terms and features of the deep-learning model, wherein the producing comprises populating a pre-defined ontology format with features of each deep-learning model; and generating a deep-learning model catalog comprising the plurality of deep-learning models, wherein the catalog comprises, for each of the deep-learning models, the ontology corresponding to the deep-learning model.

Deep-learning model catalog creation

Techniques for the suggestion and completion of deep learning models are disclosed including receiving a set of data and determining at least one property of the data. A plurality of characteristics of a computing device and a plurality of deep learning models are received and a score for each of the plurality of deep learning models is determined based on the received computing device characteristics and the determined at least one property of the data. The plurality of deep learning models are ranked for presentation to a user based on the determined scores. One or more of the deep learning models are presented on a display based on the ranking. A selection of one of the deep learning models is received and the selected deep learning model is trained using the set of data.

Suggestion and completion of deep learning models from a catalog

A mobile application update manager functioning on a user device defers a new update for a mobile application for a first time period. The mobile application update manager predicts a time and size of a next update for the mobile application, a set of changes associated with the new update, and a relevancy of the set of changes to a user of the user device. The mobile application update manager recommends if the new update should be implemented or if the user should defer until a next update is available for the mobile application.

Mobile application update manager

One embodiment provides a method, including: tracking behavior of a user when the user is providing input to a permission request of an application, wherein the permission request comprises at least one application permission requesting access for the application to information accessible by an information handling device; identifying at least one undesired application permission, wherein the identifying comprises detecting, based upon the behavior of the user, that the user is uncomfortable with the at least one undesired application permission; determining whether another similar application, having a permission set the user is comfortable with, is available, wherein the determining comprises searching for applications similar to the application and filtering the similar applications by removing applications having a permission similar to the undesired application permission; and providing a recommendation, if there is another similar application, to the user, wherein the recommendation comprises the another similar application.

Growing community of inventors

Bengaluru, India

Rahul Aralikatte