2

Efficient and Compact Representations of Deep Neural Networks via Entropy Coding

Matrix operations are nowadays central in many Machine Learning techniques, including in particular Deep Neural Networks (DNNs), whose core of any inference is represented by a sequence of dot product operations. An increasingly emerging problem is …

Neural networks as building blocks for the design of efficient learned indexes

The new area of Learned Data Structures consists of mixing Machine Learning techniques with those specific to Data Structures, with the purpose to achieve time/space gains in the performance of those latter. The perceived paradigm shift in computer …

On nonlinear learned string indexing

We investigate the potential of several artificial neural network architectures to be used as an index on a sorted set of strings, namely, as a mapping from a query string to (an estimate of) its lexicographic rank in the set, which allows solving …

A New Class of String Transformations for Compressed Text Indexing

Introduced about thirty years ago in the field of data compression, the Burrows-Wheeler Transform (BWT) is a string transformation that, besides being a booster of the performance of memoryless compressors, plays a fundamental role in the design of …

Discriminative Pattern Discovery for the Characterization of Different Network Populations

An interesting problem is to study how gene co-expression vary in two different populations, associated with healthy and unhealthy individuals, respectively. To this aim, two important aspects should be taken into account: (1) in some cases, …

Learned Sorted Table Search and Static Indexes in Small-Space Data Models

Machine-learning techniques, properly combined with data structures, have resulted in Learned Static Indexes, innovative and powerful tools that speed up Binary Searches with the use of additional space with respect to the table being searched into. …

Deep neural networks compression: A comparative survey and choice recommendations

The state-of-the-art performance for several real-world problems is currently reached by deep and, in particular, convolutional neural networks (CNN). Such learning models exploit recent results in the field of deep learning, leading to highly …

DIAMIN: a software library for the distributed analysis of large-scale molecular interaction networks

**Background** Huge amounts of molecular interaction data are continuously produced and stored in public databases. Although many bioinformatics tools have been proposed in the literature for their analysis, based on their modeling through different …

Compressing and querying integer dictionaries under linearities and repetitions

We revisit the fundamental problem of compressing an integer dictionary that supports efficient $\mathsf{rank}$ and $\mathsf{select}$ operations by exploiting simultaneously two kinds of regularities arising in real data: _repetitiveness_ and …

Standard versus uniform binary search and their variants in learned static indexing: The case of the searching on sorted data benchmarking software platform

Learned Indexes use a model to restrict the search of a sorted table to a smaller interval. Typically, a final binary search is done using the lower_bound routine of the Standard C++ library. Recent studies have shown that on current processors other …