Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies

By Anthony Kulis. Scalable Computing : Practice and Experience, 2009

355 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/c866b5d3059cf63cd4f27e0b7b0e9c2096394c54

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Systemic Risks in Society and Economics (2010, positive): “This is, for example, relevant for the possibility of collective intelligence [134–136].”
Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks (2017, methodology): “ANNs are graph-based structures that are simplified, abstract computational models of real brains in which the nodes and connections of the graph correspond to neurons and synapses [8, 9].”
Genetic Representation and Evolvability of Modular Neural Controllers (2010, background): “Evolved control architectures are often surprisingly different from hand-designed systems and sometimes more efficient in terms of computational requirements [16].”
Neural Modularity Helps Organisms Evolve to Learn New Skills without Forgetting Old Skills (2015, methodology): “Evolutionary algorithms frequently get stuck in local optima [5] and, due to computational costs, are limited to small population sizes compared to biological evolution.”
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review (2017, methodology): “Biology has inspired several artificial intelligence techniques such as ANNs, evolutionary algorithms, and cellular automata (Floreano & Mattiussi, 2008).”
Artificial Evolution of Plastic Neural Networks: A Few Key Concepts (2014, background): “Natural adaptive processes are classically divided into three main categories, each of them having been a continuous source of inspiration in artiﬁcial intelligence and robotics [8]: evolution, development and learning.”
Survey on Coverage Path Planning with Unmanned Aerial Vehicles (2019, background): “Thus biologically-inspired approaches consisting of algorithms based on fundamental aspects of natural intelligence have emerged, such as behavioral autonomy and social interaction, evolution and learning [70].”
Neuromodulation Improves the Evolution of Forward Models (2016, background): “Specifically, NE builds a population of candidate networks and then refine them by applying small changes (mutations) [10].”
Bio inspired computing - A review of algorithms and scope of applications (2016, background): “Particle swarm optimization is used for problems where the function to be optimized is discontinuous, non-differentiable with too many nonlinearly related parameters (Floreano & Mattiussi, 2008).”
Swarm Robotic Behaviors and Current Applications (2020, background): “Floreano and Mattiussi (2008) discuss swarm intelligence alongside evolutionary computation, artiﬁcial neural networks, and bio robotics.”
A distribution network expansion planning model considering distributed generation options and techo-economical issues (2010, methodology): “This idea is used to deal with optimization problems by considering the objective functions and the constraints as antigens while the solutions construct the antibodies [28].”
Using a map-based encoding to evolve plastic neural networks (2011, background): “Evolved ANNs show impressive results as controllers for autonomous robots and artificial agents [1]–[3].”
On the Impact of Robotics in Behavioral and Cognitive Sciences: From Insect Navigation to Human Cognitive Development (2010, neutral): “ming of robots [4], [6], [10], [15], [36], [52].”
Illuminating search spaces by mapping elites (2015, methodology): “Specifically, we test (1) whether MAP-Elites can produce a large diversity of morphologies within one run and (2) whether it can produce high-performing morphologies for a range of levels of bone use and body size, and combinations thereof.”