Computational Power of Threshold Circuits of Energy at most Two

2018 ◽  
Vol E101.A (9) ◽  
pp. 1431-1439
Author(s):  
Hiroki MANIWA ◽  
Takayuki OKI ◽  
Akira SUZUKI ◽  
Kei UCHIZAWA ◽  
Xiao ZHOU
Keyword(s):  
Computational Power ◽  
Threshold Circuits

Lower Bounds for the Computational Power of Networks of Spiking Neurons

1996 ◽  
Vol 8 (1) ◽  
pp. 1-40 ◽  
Author(s):  
Wolfgang Maass
Keyword(s):  
Formal Model ◽  
Random Access ◽  
Spiking Neurons ◽  
Turing Machines ◽  
Computational Power ◽  
Computational Tool ◽  
Threshold Functions ◽  
Basic Assumptions ◽  
Threshold Circuits ◽  
Phase Differences

We investigate the computational power of a formal model for networks of spiking neurons. It is shown that simple operations on phase differences between spike-trains provide a very powerful computational tool that can in principle be used to carry out highly complex computations on a small network of spiking neurons. We construct networks of spiking neurons that simulate arbitrary threshold circuits, Turing machines, and a certain type of random access machines with real valued inputs. We also show that relatively weak basic assumptions about the response and threshold functions of the spiking neurons are sufficient to employ them for such computations.

On the Computational Power of Threshold Circuits with Sparse Activity

2006 ◽  
Vol 18 (12) ◽  
pp. 2994-3008 ◽  
Author(s):  
Kei Uchizawa ◽  
Rodney Douglas ◽  
Wolfgang Maass
Keyword(s):  
Neural Circuits ◽  
Circuit Complexity ◽  
Complexity Measure ◽  
Computational Power ◽  
Complexity Measures ◽  
Threshold Circuit ◽  
Polynomial Size ◽  
Threshold Circuits ◽  
Size Threshold ◽  
The Brain

Circuits composed of threshold gates (McCulloch-Pitts neurons, or perceptrons) are simplified models of neural circuits with the advantage that they are theoretically more tractable than their biological counterparts. However, when such threshold circuits are designed to perform a specific computational task, they usually differ in one important respect from computations in the brain: they require very high activity. On average every second threshold gate fires (sets a 1 as output) during a computation. By contrast, the activity of neurons in the brain is much sparser, with only about 1% of neurons firing. This mismatch between threshold and neuronal circuits is due to the particular complexity measures (circuit size and circuit depth) that have been minimized in previous threshold circuit constructions. In this letter, we investigate a new complexity measure for threshold circuits, energy complexity, whose minimization yields computations with sparse activity. We prove that all computations by threshold circuits of polynomial size with entropy O(log n) can be restructured so that their energy complexity is reduced to a level near the entropy of circuit states. This entropy of circuit states is a novel circuit complexity measure, which is of interest not only in the context of threshold circuits but for circuit complexity in general. As an example of how this measure can be applied, we show that any polynomial size threshold circuit with entropy O(log n) can be simulated by a polynomial size threshold circuit of depth 3. Our results demonstrate that the structure of circuits that result from a minimization of their energy complexity is quite different from the structure that results from a minimization of previously considered complexity measures, and potentially closer to the structure of neural circuits in the nervous system. In particular, different pathways are activated in these circuits for different classes of inputs. This letter shows that such circuits with sparse activity have a surprisingly large computational power.

Current Scenario in Structure and Ligand-Based Drug Design on Anti-colon Cancer Drugs

2019 ◽  
Vol 24 (32) ◽  
pp. 3829-3841 ◽  
Author(s):  
Lakshmanan Loganathan ◽  
Karthikeyan Muthusamy
Keyword(s):  
Drug Discovery ◽  
Drug Design ◽  
Anticancer Agent ◽  
Computational Power ◽  
Cancer Drugs ◽  
Recent Advances ◽  
Anti Cancer ◽  
Drug Designing ◽  
Current Scenario ◽  
Molecular Modeling Studies

Worldwide, colorectal cancer takes up the third position in commonly detected cancer and fourth in cancer mortality. Recent progress in molecular modeling studies has led to significant success in drug discovery using structure and ligand-based methods. This study highlights aspects of the anticancer drug design. The structure and ligand-based drug design are discussed to investigate the molecular and quantum mechanics in anti-cancer drugs. Recent advances in anticancer agent identification driven by structural and molecular insights are presented. As a result, the recent advances in the field and the current scenario in drug designing of cancer drugs are discussed. This review provides information on how cancer drugs were formulated and identified using computational power by the drug discovery society.

A Human/Computer Learning Network to Improve Biodiversity Conservation and Research

AI Magazine ◽  
2012 ◽  
Vol 34 (1) ◽  
pp. 10 ◽  
Author(s):  
Steve Kelling ◽  
Jeff Gerbracht ◽  
Daniel Fink ◽  
Carl Lagoze ◽  
Weng-Keen Wong ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Feedback Loop ◽  
Human Computation ◽  
Computational Power ◽  
Learning Networks ◽  
Learning Network ◽  
Computer Learning ◽  
The Individual ◽  
Citizen Science Project

In this paper we describe eBird, a citizen-science project that takes advantage of the human observational capacity to identify birds to species, which is then used to accurately represent patterns of bird occurrences across broad spatial and temporal extents. eBird employs artificial intelligence techniques such as machine learning to improve data quality by taking advantage of the synergies between human computation and mechanical computation. We call this a Human-Computer Learning Network, whose core is an active learning feedback loop between humans and machines that dramatically improves the quality of both, and thereby continually improves the effectiveness of the network as a whole. In this paper we explore how Human-Computer Learning Networks can leverage the contributions of a broad recruitment of human observers and processes their contributed data with Artificial Intelligence algorithms leading to a computational power that far exceeds the sum of the individual parts.

The computational power of monodirectional tissue P systems with symport rules

2021 ◽  
pp. 104751
Author(s):  
Bosheng Song ◽  
Shengye Huang ◽  
Xiangxiang Zeng
Keyword(s):  
P Systems ◽  
Computational Power

scholarly journals Towards efficient verification of population protocols

2021 ◽  
Author(s):  
Michael Blondin ◽  
Javier Esparza ◽  
Stefan Jaax ◽  
Philipp J. Meyer
Keyword(s):  
Linear Constraints ◽  
Computational Power ◽  
High Complexity ◽  
Reachability Problem ◽  
Population Protocols ◽  
Finite State ◽  
State Agents ◽  
Efficient Verification ◽  
Primitive Recursive ◽  
Very High

AbstractPopulation protocols are a well established model of computation by anonymous, identical finite-state agents. A protocol is well-specified if from every initial configuration, all fair executions of the protocol reach a common consensus. The central verification question for population protocols is the well-specification problem: deciding if a given protocol is well-specified. Esparza et al. have recently shown that this problem is decidable, but with very high complexity: it is at least as hard as the Petri net reachability problem, which is -hard, and for which only algorithms of non-primitive recursive complexity are currently known. In this paper we introduce the class $${ WS}^3$$ WS 3 of well-specified strongly-silent protocols and we prove that it is suitable for automatic verification. More precisely, we show that $${ WS}^3$$ WS 3 has the same computational power as general well-specified protocols, and captures standard protocols from the literature. Moreover, we show that the membership and correctness problems for $${ WS}^3$$ WS 3 reduce to solving boolean combinations of linear constraints over $${\mathbb {N}}$$ N . This allowed us to develop the first software able to automatically prove correctness for all of the infinitely many possible inputs.

scholarly journals A Review on Human–AI Interaction in Machine Learning and Insights for Medical Applications

2021 ◽  
Vol 18 (4) ◽  
pp. 2121
Author(s):  
Mansoureh Maadi ◽  
Hadi Akbarzadeh Khorshidi ◽  
Uwe Aickelin
Keyword(s):  
Machine Learning ◽  
Future Research ◽  
Computational Power ◽  
Medical Field ◽  
Interactive Machine Learning ◽  
Human In The Loop ◽  
Human Interactions ◽  
Scoping Literature Review ◽  
Domain Expertise ◽  
Expertise Level

Objective: To provide a human–Artificial Intelligence (AI) interaction review for Machine Learning (ML) applications to inform how to best combine both human domain expertise and computational power of ML methods. The review focuses on the medical field, as the medical ML application literature highlights a special necessity of medical experts collaborating with ML approaches. Methods: A scoping literature review is performed on Scopus and Google Scholar using the terms “human in the loop”, “human in the loop machine learning”, and “interactive machine learning”. Peer-reviewed papers published from 2015 to 2020 are included in our review. Results: We design four questions to investigate and describe human–AI interaction in ML applications. These questions are “Why should humans be in the loop?”, “Where does human–AI interaction occur in the ML processes?”, “Who are the humans in the loop?”, and “How do humans interact with ML in Human-In-the-Loop ML (HILML)?”. To answer the first question, we describe three main reasons regarding the importance of human involvement in ML applications. To address the second question, human–AI interaction is investigated in three main algorithmic stages: 1. data producing and pre-processing; 2. ML modelling; and 3. ML evaluation and refinement. The importance of the expertise level of the humans in human–AI interaction is described to answer the third question. The number of human interactions in HILML is grouped into three categories to address the fourth question. We conclude the paper by offering a discussion on open opportunities for future research in HILML.

Sign in / Sign up

Export Citation Format

Share Document