You are currently viewing a new version of our website. To view the old version click .

Algorithms, Volume 15, Issue 12

December 2022 - 45 articles

Cover Story: Is the decision process of artificial neural networks comparable to that of humans? Are their predictions influenced by the same features? This work aims to answer these questions by presenting a study on how human understandable concepts emerge in the internal layers of a neural transformer, trained in the detection of software vulnerabilities. We first determine some domain-specific concepts (e.g., the presence of given patterns in the source code), and for each concept we train support vector classifiers to separate points in the vector activations spaces that represent input instances with the concept from those without the concept. Then, we study if the presence (or the absence) of such concepts affects the inference of the neural network on its original task. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
  • You may sign up for email alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.

Articles (45)

  • Article
  • Open Access
4 Citations
2,831 Views
12 Pages

Stochastic Safety Radius on UPGMA

  • Ruriko Yoshida,
  • Lillian Paul and
  • Peter Nesbitt

18 December 2022

Unweighted Pair Group Method with Arithmetic Mean (UPGMA) is one of the most popular distance-based methods to reconstruct an equidistant phylogenetic tree from a distance matrix computed from an alignment of sequences. Since we use equidistant trees...

  • Article
  • Open Access
2 Citations
2,097 Views
11 Pages

Thermal Conductivity of Low-GWP Refrigerants Modeling with Multi-Object Optimization

  • Mariano Pierantozzi,
  • Sebastiano Tomassetti and
  • Giovanni Di Nicola

17 December 2022

In this paper, the procedure of finding the coefficients of an equation to describe the thermal conductivity of refrigerants low in global warming potential (GWP) is transformed into a multi-objective optimization problem by constructing a multi-obje...

  • Article
  • Open Access
6 Citations
2,196 Views
14 Pages

17 December 2022

Connectivity in large-scale data center networks is a critical indicator to evaluate network state. A feasible and performance-guaranteed algorithm enables us to find disjoint paths between network vertices to ensure effective data transfer and to ma...

  • Article
  • Open Access
3 Citations
2,559 Views
16 Pages

16 December 2022

The evaluation of the fault diagnosis capability of a data center network (DCN) is important research in measuring network reliability. The g-extra diagnosability is defined under the condition that every component except the fault vertex set contain...

  • Article
  • Open Access
2,194 Views
15 Pages

16 December 2022

It has been proven that extended resolution (ER) has more powerful reasoning than general resolution for the pigeonhole principle in Cook’s paper. This fact indicates the possibility that a solver based on extended resolution can exceed Boolean...

  • Article
  • Open Access
1 Citations
1,850 Views
30 Pages

15 December 2022

The problem of wildfire spread prediction presents a high degree of complexity due in large part to the limitations for providing accurate input parameters in real time (e.g., wind speed, temperature, moisture of the soil, etc.). This uncertainty in...

  • Article
  • Open Access
7 Citations
8,972 Views
16 Pages

15 December 2022

The Theta* algorithm is a path planning algorithm based on graph search, which gives the optimal path with more flexibility than A* algorithm in terms of routes. The traditional Theta* algorithm is difficult to take into account with the global and d...

  • Article
  • Open Access
2,959 Views
19 Pages

On Deep-Fake Stock Prices and Why Investor Behavior Might Not Matter

  • Călin Vâlsan,
  • Elena Druică and
  • Eric Eisenstat

15 December 2022

We propose an agent-based model of financial markets with only one asset. Thirty-two agents follow very simple rules inspired by Wolfram’s Rule 110. They engage in buying, selling, and/or holding. Each agent is endowed with a starting balance s...

of 5

Get Alerted

Add your email address to receive forthcoming issues of this journal.

XFacebookLinkedIn
Algorithms - ISSN 1999-4893