Analog Genetic Encoding for the Evolution of Circuits and Networks

By Claudio Mattiussi, Dario Floreano. 2007

157 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Molecular Biology

How researchers see this paper

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

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, methodology): “with AGE (Mattiussi and Floreano, 2007) for video game playing were shown to perform better with the addition of neuromodulation.”
Evolutionary and Computational Advantages of Neuromodulated Plasticity (2008, background): “An overview is given here, further detail can be found in the literature (Mattiussi, 2005; Mattiussi and Floreano, 2007; Dürr et al., 2006; Marbach et al., 2007).”
Evolution of Plastic Learning in Spiking Networks via Memristive Connections (2012, background): “A number of encoding variants have been developed specifically for neuroevolution, including analog genetic encoding [50], which allows for both neurons and connections to be modified, amongst others (e.”
Autonomous Evolution of Topographic Regularities in Artificial Neural Networks (2010, background): “…ﬁeld of generative and developmental systems , the subﬁeld of evolutionary computation from which HyperNEAT originates (Astor & Adami, 2000; Bentley & Kumar, 1999; Eggenberger, 1997; Hornby & Pollack, 2002; Lindenmayer, 1974; Mattiussi & Floreano, 2007; Stanley & Miikkulainen, 2003; Turing, 1952).”
Emergent vision system of autonomous virtual characters (2016, methodology): “The genetic encoding presented in this work is a simpli ﬁ ed version of the Analog Genetic Encoding (AGE) [30], focused on the evolution of the neuromodulated network described in the previous section.”
Evolving neuromodulatory topologies for reinforcement learning-like problems (2007, methodology): “Following, an overview of the algorithm is given.”
On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks (2013, background): “Inﬂuenced by this concept, many researchers proposed artiﬁcial developmental systems with diverse inspirations including chemical gradients [11,12], gene regulatory networks [13,14], cell divisions [15], computational neuro-science models [16] and L-systems [9].”
Evolving Plastic Neuromodulated Networks for Behavior Emergence of Autonomous Virtual Characters (2013, methodology): “Similar to what is done in AGE, we pair neurons by their terminals to create the synapses arriving at or leaving the neurons.”
Evolving Spiking Networks with Variable Resistive Memories (2014, methodology): “A number of encoding variants have been developed specifically for neuroevolution, including analog genetic encoding (AGE; Mattiussi and Floreano, 2007), which allows for both neurons and connections to be modified, among others (Jung and Reggia, 2006).”
Genetic Representation and Evolvability of Modular Neural Controllers (2010, methodology): “In [45], an implicit encoding called Analog Genetic Encoding (AGE, [48]) was evaluated in the same pole-balancing problem mentioned above.”