Vito Walter Anelli's repositories
Google-HashCode-Playground
This project allows to evaluate your submissions for past editions of Google HashCode.
OpenCV-GPU-matchTemplate
The OpenCV matchTemplate primitive for gpu has been adapted in order to enable calculations on 32-bit floating-point raw data.
FaceAccess-Android-Biometric-Recognition
This twofold app (Mobile App and Server App) let you to authenticate yourself with your face, login and password and it recognizes who you are in a community.
Hashcode2019F-kingKarma
This is the solution we implemented during the Google Hashcode 2019 Extended Round - 1,232,411 points - 23rd World rank
suDO-Android-Sudoku-Solver
This is an Android project that let the user to take a photo to a Sudoku grid and it solves it automatically.
DatasetsSplits
This is a collection of splittings of publicly available Datasets. This collection has been created for two main purposes:
Features-Factorization
Features-Factorization and Feature Spreading Relevance (Knowledge-aware Recommender Systems)
HybridFactorizationMachines
kaHFM relies on Factorization Machines and it extends them in different key aspects making use of the semantic information encoded in a knowledge graph
papers-results
Papers Results
recommenders
Recommender Systems algorithms implementations
The-importance-of-being-dissimilar-in-Recommendation
Similarity measures play a fundamental role in memory-based nearest neighbors approaches. They recommend items to a user based on the similarity of either items or users in a neighborhood. In this paper we argue that, although it keeps a leading importance in computing recommendations, similarity between users or items should be paired with a value of dissimilarity (computed not just as the complement of the similarity one). We formally modeled and injected this notion in some of the most used similarity measures and evaluated our approach showing its effectiveness in terms of accuracy results.