Abstract: 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.

Abstract: A method, computer system, and a computer program product for automatically recommending a plurality of text snippets from a book script for a movie adaptation is provided. The present invention may include receiving, by a user, a piece of input data, wherein the input data includes the book script, and a plurality of past book-to-movie adaptations. The present invention may then include identifying a plurality of text snippets associated with the received book script. The present invention may also include recommending the plurality of text snippets associated with the received book script to include in a movie based on the plurality of past book-to-movie adaptations and a plurality of movie reviews corresponding with the plurality of past book-to-movie adaptations.

Abstract: Embodiments describe an approach for automatically generating feedback for an online forum. Embodiments determine if a user is using a solution to a problem, wherein the solution is posted on an online forum, and responsive to determining the user is using the solution, capturing environment information associated with the user's computing device. Additionally, embodiments determine if the solution solved the problem, and responsive to determining the solution solved the problem, automatically generate feedback associated with the solution, wherein the feedback comprises the environment information and information detailing that the solution solved the problem.

Abstract: Methods, systems and computer program products for wastage estimation are provided herein. A computer-implemented method includes receiving, via a user interface, selection of a product for which an estimation of wastage incurred in manufacture thereof is desired and determining one or more orientation suggestions for the selected product, the one or more orientation suggestions including suggestions for imaging different views of the selected product for use in estimating the wastage incurred in manufacture thereof. The method also includes providing, via the user interface, one or more prompts for imaging the selected product at the one or more orientation suggestions, thereby obtaining images of the selected product, utilizing the obtained images of the selected product to calculate an estimated wastage incurred in manufacturing the selected product, and displaying, via the user interface, a display element indicating the estimated wastage incurred in manufacturing the selected product.

Abstract: One embodiment provides a method, including: creating, for a user, a sound desirability index comprising (i) a plurality of sounds and (ii) desirability of the sound to the user with respect to each of the plurality of sounds, wherein the sound desirability index is created in response to the user hearing a sound and the environment of the user when hearing the sound; receiving an audible input within hearing proximity of the user; identifying the current environment of the user; determining the desirability of the audible input to the user by accessing the sound desirability index, and determining the desirability of the audible input based upon a sound in the audible input and the current environment of the user; and modifying a characteristic of at least a portion of the audible input based upon the desirability of the audible input to the user.

Abstract: Methods, apparatus, and processor-readable storage media for facilitating a secure platform for point-to-point brain sensing are provided herein. An exemplary method includes presenting a user of a brain-computer interface with learning content; monitoring brain signals of the user using a brain-computer interface while the learning content is being presented; determining, based at least in part on said monitoring, that a confusion state of the user exceeds a personalized confusion threshold in regard to at least a part of the learning content; in response to said determining, outputting information to assist the user in understanding the part of the learning content until the confusion state of the user is below the personalized confusion threshold.

Abstract: One embodiment provides a method, including: providing, at a collaborative deep learning model authoring tool, a dialog window that (i) receives user inputs discussing deep learning model aspects and (ii) provides recommendations from the collaborative deep learning model authoring tool; providing, at the collaborative deep learning model authoring tool, a consensus view indicating (i) a conflicting aspect identified as an aspect where more than one user selected a different aspect and (ii) the aspect selected for implementation within the deep learning model based upon that aspect having the most user selections; providing, at the collaborative deep learning model authoring tool, a model view displaying layers of the deep learning model based upon (i) aspects selected by the users in the dialog window and (ii) the aspect selected for implementation in the consensus view; and providing, at the collaborative deep learning model authoring tool, a deployment view that displays an execution of the deep learning m

Abstract: One embodiment provides a method, including: receiving a script for a performance requiring at least one actor; receiving a profile for each of a plurality of actors, wherein each actor profile identifies attributes of the corresponding actor; identifying a given portion of the script to be used for an audition of at least one of the plurality of actors, wherein the identifying comprises (i) evaluating aspects of each portion of the script, (ii) scoring, based upon the evaluation, each portion of the script, and (iii) ranking the portions of the script based upon the score; selecting at least one actor from the plurality of actors for performance of the audition corresponding to the given portion of the script, wherein the selecting comprises evaluating attributes of the actors with respect to the given portion of the script; and recommending at least one actor and at least one portion of the script for an audition based upon the selected at least one actor.

Abstract: Methods, systems, and computer program products for generating collaborative orderings of information pertaining to products to present to target users are provided herein.

Abstract: 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.

Abstract: One embodiment provides a method, including: creating, for a user, a sound desirability index comprising (i) a plurality of sounds and (ii) desirability of the sound to the user with respect to each of the plurality of sounds, wherein the sound desirability index is created in response to the user hearing a sound and the environment of the user when hearing the sound; receiving an audible input within hearing proximity of the user; identifying the current environment of the user; determining the desirability of the audible input to the user by accessing the sound desirability index, and determining the desirability of the audible input based upon a sound in the audible input and the current environment of the user; and modifying a characteristic of at least a portion of the audible input based upon the desirability of the audible input to the user.

Abstract: Methods, systems and computer program products for wastage estimation are provided herein. A computer-implemented method includes receiving, via a user interface, selection of a product for which an estimation of wastage incurred in manufacture thereof is desired and determining one or more orientation suggestions for the selected product, the one or more orientation suggestions including suggestions for imaging different views of the selected product for use in estimating the wastage incurred in manufacture thereof. The method also includes providing, via the user interface, one or more prompts for imaging the selected product at the one or more orientation suggestions, thereby obtaining images of the selected product, utilizing the obtained images of the selected product to calculate an estimated wastage incurred in manufacturing the selected product, and displaying, via the user interface, a display element indicating the estimated wastage incurred in manufacturing the selected product.

Abstract: Aspects of the present invention disclose a method, computer program product, and system for recommending an apparel product is provided. The method for recommending an apparel product may include one or more processors identifying a user selection of an apparel product, wherein the apparel product includes information associated with retail websites. The method further includes one or more processors categorizing the apparel product into one or more groupings based upon user preferences, wherein the grouping is based on available versions of the apparel product. The method further includes one or more processors determining current apparel preference information corresponding to the user based on user preferences, fitness application data, health monitoring application data, and user-provided measurements.

Abstract: One embodiment a method for ensuring group cohesiveness, the method including: utilizing at least one processor to execute computer code that performs the steps of: obtaining community information associated with a group; generating, based on the community information, a group profile; detecting a user action; determining, based on the group profile, if the user action negatively affects group cohesiveness; and generating, based on the determining, a notification. Other aspects are described and claimed.

Abstract: One embodiment provides a method, including: receiving a user wardrobe query related to at least one item in a user's wardrobe to be worn for an event, wherein the user wardrobe query corresponds to at least one of an outfit recommendation query and an outfit sharing query; accessing a database comprising user profiles, each of the user profiles comprising (i) a listing of the at least one item in a user's wardrobe, (ii) at least one attribute of a user, and (iii) feature information for each of the at least one items indicating a feature of the item; determining at least one score for each of the at least one items; and providing at least one recommendation responsive to the user wardrobe query, wherein the at least one recommendation comprises an item from the user's wardrobe or another user's wardrobe having a score above a predetermined threshold.

Abstract: A method for building a user wardrobe profile of an individual user within a group having a group account ID. The method receives purchase transaction data associated with the group account ID data, wherein the purchase transaction data comprises data for one or more wardrobe items. The method further detects, in one or more social media posts of the individual user, an electronic representation of the one or more wardrobe items in the purchase transaction data, and builds the user wardrobe profile of the individual user, based on an association between the purchase transaction data and the electronic representation of the one or more wardrobe items detected in the one or more social media posts of the individual user.

Abstract: Methods and arrangements for forecasting at least one attribute of a future event based on a repository of historical event data associated with historical events comparable to the future event. A plurality of event data points are obtained from the repository of historical event data. The plurality of event data points are grouped in accordance with at least one category and a plurality of subcategories to create at least one data tree. Certain of the grouped event data points are designated to form a set of candidate data attributes, and the designated set of candidate data attributes are compared to a set of data attributes from the at least one data tree associated with the future event. Based on the comparing, there is identified a data attribute missing from the set of data attributes from the at least one data tree associated with the future event, and a value for the missing data attribute is forecast. Other variants and embodiments are broadly contemplated herein.

Abstract: A movie review generating method, system, and computer program product for dynamically generating movie reviews by capturing and aggregating the experience observed by an external observation system, and correlating the observation with the elements of the movie by creating soft-faceted boundaries around the elements.

Abstract: One embodiment provides a method, including: utilizing at least one processor to execute computer code that performs the steps of: capturing a wireless signal of a target entity, wherein the wireless signal provides the direction of the target entity with respect to a traveling entity; generating a location profile for the traveling entity, wherein the generating comprises: capturing, using an image capture device, at least one image of the environment surrounding the traveling entity; and determining movement information of the traveling entity, wherein the movement information comprises directional information and speed information; determining the location of the target entity, in view of the environment surrounding the traveling entity; and providing navigation details based upon the location profile, wherein the navigation details comprise instructions for navigating from the location of the traveling entity to the location of the target entity. Other aspects are described and claimed.

Abstract: One embodiment provides a method, including: utilizing at least one processor to execute computer code that performs the steps of: capturing a wireless signal of a target entity, wherein the wireless signal provides the direction of the target entity with respect to a traveling entity; generating a location profile for the traveling entity, wherein the generating comprises: capturing, using an image capture device, at least one image of the environment surrounding the traveling entity; and determining movement information of the traveling entity, wherein the movement information comprises directional information and speed information; determining the location of the target entity, in view of the environment surrounding the traveling entity; and providing navigation details based upon the location profile, wherein the navigation details comprise instructions for navigating from the location of the traveling entity to the location of the target entity. Other aspects are described and claimed.