No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
Discrimination Learning Guided By Instinct
Abstract
Complex organisms exhibit both evolved instincts and experiential learning as adaptive mechanisms. In isolation, neither mechanism is sufficient to successfully navigate the environments of such organisms. Instincts provide behaviors that are generally adaptive but fail in specific cases. Learning must rely on some internal or external guidance to succeed on challenging tasks. This paper explores how instincts and experiential learning can work in tandem to solve a maze environment. Specifically, instincts comprise general knowledge of a set of related mazes representing worlds that an organism might be born into, and experiential learning discriminates specific situations in the particular maze world that an organism is born into. Synergy is accomplished by a hybrid neural network, one part instinctive and the other part capable of learning. After sufficient discriminating experiences, learning can override instinct to navigate a maze when instinct would otherwise fail. Results show a marked improvement in performance when this synergistic approach is employed relative to using either instincts or learning in isolation.
... I have previously conducted research into a number of issues that differentiate conventional AI from natural intelligence. These include context, motivation, plasticity, modularity, instinct, and surprise (Portegys 2007(Portegys , 2010(Portegys , 2013(Portegys , 2015. Morphognosis, in particular, has been previously applied to the task of nest-building by a species of pufferfish (Portegys 2019). ...
Honey bees are social insects that forage for flower nectar cooperatively. When an individual forager discovers a flower patch rich in nectar, it returns to the hive and performs a “waggle dance” in the vicinity of other bees that consists of movements communicating the direction and distance to the nectar source. The dance recruits “witnessing” bees to fly to the location of the nectar to retrieve it, thus cooperatively exploiting the environment. Replicating such complex animal behavior is a step forward on the path to artificial intelligence. This project simulates the bee foraging behavior in a cellular automaton using the Morphognosis machine learning model. The model features hierarchical spatial and temporal contexts that output motor responses from sensory inputs. Given a set of bee foraging and dancing exemplars, and exposing only the external input-output of these behaviors to the Morphognosis learning algorithm, a hive of artificial bees can be generated that forage as their biological counterparts do. A comparison of Morphognosis foraging performance with that of an artificial recurrent neural network is also presented.KeywordsHoney bee foraging danceMorphognosisArtificial animal intelligenceArtificial neural networkMachine learningArtificial life
... I have previously conducted research into a number of issues that differentiate conventional AI from natural intelligence. These include context, motivation, plasticity, modularity, instinct, and surprise (Portegys 2007(Portegys , 2010(Portegys , 2013(Portegys , 2015. Morphognosis, in particular, has been previously applied to the task of nest-building by a species of pufferfish (Portegys 2019). ...
A bstract
Honey bees are social insects that forage for flower nectar cooperatively. When an individual forager discovers a flower patch rich in nectar, it returns to the hive and performs a “dance” in the vicinity of other bees that consists of movements communicating the direction and distance to the nectar source. The bees that receive this information then fly to the location of the nectar to retrieve it, thus cooperatively exploiting the environment. This project simulates this behavior in a cellular automaton using the Morphognosis model. The model features hierarchical spatial and temporal contexts that output motor responses from sensory inputs. Given a set of bee foraging and dancing exemplars, and exposing only the external input-output of these behaviors to the Morphognosis learning algorithm, a hive of artificial bees can be generated that forage as their biological counterparts do.
Mona is a goal
-
seeking
artificial
neural network
(ANN)
that learns hierarchie
s of cause and
effect contexts
. These contexts
allow Mona
to predict future events.
The structure of the
environment is modeled
in
long
-
term memory; the state of the environment is modeled
in
working memory. Mona is an active system: it
uses
environmental contexts
to produce
responses
that
navigate the environment toward goal events that
satisfy internal needs. Goal
-
seeking thus also filters learning to retain more relevant information about the environment.
An architecture is presented for robot control which can be viewed as a very fine-grained layered architecture motivated by the principles underlying the subsumption architecture. The subsumption architecture provides a powerful means for defining intelligent robot control mechanisms through the layered composition of simple behaviors. However, the authors have found that there are basic limitations inherent in this architecture due to the inaccessibility of information internal to a behavior. While adhering to the basic concept of building a robot control system through successive layers of competence, task-achieving behavior in this system is fragmented into many smaller decision-making units. Each of these units simply has the task of transforming a set of input activations into an output activation, so that the role that any unit plays in the system is defined entirely by how it is connected to other units. This fine-grained nature of the architecture permits a more flexible arbitration of commands between behaviors and provides incrementally added behaviors with complete access to the internal state of existing behaviors.< >
Instinct and experience are shown to form a potent combination to achieve effective foraging in a simulated environment. A neural network capable of evolving instinct-related neurons and learning from experience is used as the brain of a simple foraging creature that must find food and water in a 3D block world. Instincts provide basic tactics for unsupervised exploration of the world, allowing pathways to food and water to be learned. The combination of both instinct and experience was found to be more effective than either alone. As a comparison, neural network learning also proved superior to Q-Learning on the foraging task.
The paper describes simulations on populations of neural networks that both evolve at the population level and learn at the individual level. Unlike other simulations, the evolutionary task (finding food in the environment) and the learning task (predicting the next position of food on the basis of present position and planned network's movement) are different tasks. In these conditions both learning influences evolution (without Lamarckian inheritance of learned weight changes) and evolution influences learning. Average but not peak fitness has a better evolutionary growth with learning than without learning. After the initial generations individuals that learn to predict during life also improve their food finding ability during life. Furthermore, individuals which inherit an innate capacity to find food also inherit an innate predisposition to learn to predict the sensory consequences of their movements. They do not predict better at birth but they do learn to predict bett...
The concept of instinct has fallen into disrepute, due to a number of problems with the way it had been conceived, mostly
related to the concept of innateness. Yet the legacy of instincts survives in sociobiology and evolutionary psychology, in
the form of an emphasis on the genetic determinants of behavior. Through a consideration of the two main theories of instinct
and the objections that have been raised against them, it becomes clear that existing theories of instinct founder because
of their inability to reconcile the psychic and physiological “faces” of instinct. Merleau-Ponty's notion of “being-in-the-world”
as a third term linking the psychic and the physiological makes possible a new conception of instinct which escapes these
criticisms. At the same time, it opens up a new way of understanding how instincts may operate in human beings.
Newborns, ranging from 12 to 36 hours of age, produced significantly more sucking responses in order to see an image of their mothers' faces as opposed to an image of strangers' faces using a preferential operant sucking procedure.
Time underlies many interesting human behaviors. Thus, the question of how to represent time in connectionist models is very important. One approach is to represent time implicitly by its effects on processing rather than explicitly (as in a spatial representation). The current report develops a proposal along these lines first described by Jordan (1986) which involves the use of recurrent links in order to provide networks with a dynamic memory. In this approach, hidden unit patterns are fed back to themselves; the internal representations which develop thus reflect task demands in the context of prior internal states. A set of simulations is reported which range from relatively simple problems (temporal version of XOR) to discovering syntactic/semantic features for words. The networks are able to learn interesting internal representations which incorporate task demands with memory demands; indeed, in this approach the notion of memory is inextricably bound up with task processing. These representations reveal a rich structure, which allows them to be highly context-dependent, while also expressing generalizations across classes of items. These representations suggest a method for representing lexical categories and the type/token distinction.
The assumption that acquired characteristics are not inherited is often taken to imply that the adaptations that an organism learns during its lifetime cannot guide the course of evolution. This inference is incorrect (Baldwin, 1896). Learning alters the shape of the search space in which evolution operates and thereby provides good evolutionary paths towards sets of co-adapted alleles. We demonstrate that this effect allows learning organisms to evolve much faster than their nonlearning equivalents, even though the characteristics acquired by the phenotype are not communicated to the genotype.
This paper explores the capabilities of continuous time recur- rent neural networks (CTRNNs) to display reinforcement learning-like abilities on a set of T-Maze and double T-Maze navigation tasks, where the robot has to locate and "remember" the position of a reward-zone. The "learning" comes about without modifications of synapse strengths, but simply from internal network dynamics, as proposed by (12). Neural controllers are evolved in simulation and in the simple case evaluated on a real robot. The evolved controllers are analyzed and the results obtained are discussed.
In this paper, we present a bio-inspired learning methodology based on swarm particle optimization to learn both weights and topology of a multilayer feedforward neural network. The training algorithm represents a novel adaptive version of the particle swarm algorithm where the inertia weight is improved to increase the accuracy of the neural network. In addition to the updated exploration parameter, the proposed algorithm encloses a new acceleration parameter to deal with the convergence rate. In fact, the adopted optimization strategy aims to simulate a mutation rate with higher values in the favor of a global search. The swarm-based feedforward neural network was tested with benchmarking problems which includes both classification and regression problems. Some results are also presented to evaluate the algorithm performances.
Learning and evolution are two fundamental forms of adaptation. There has been a great interest in combining learning and evolution with neural networks in recent years. This paper presents a hybrid learning system for learning and designing of neural network ensembles based on negative correlation learning and evolutionary learning. The idea of the hybrid learning system is to regard the population of neural networks as an ensemble, and the evolutionary process as the design of neural network ensembles. Two tness sharing techniques have been used in the evolutionary process. One is based on the covering set. The other is to use the concept of mutual information. The effectiveness of such hybrid learning approach was tested on two real-world problems.
The evolution of a population can be guided by phenotypic traits acquired by members of that population during their lifetime. This phenomenon, known as the Baldwin Effect, can speed the evolutionary process as traits that are initially acquired become genetically specified in later generations. This paper presents conditions under which this genetic assimilation can take place. As well as the benefits that lifetime adaptation can give a population, there may be a cost to be paid for that adaptive ability. It is the evolutionary trade-off between these costs and benefits that provides the selection pressure for acquired traits to become genetically specified. It is also noted that genotypic space, in which evolution operates, and phenotypic space, on which adaptive processes (such as learning) operate, are, in general, of a different nature. To guarantee an acquired characteristic can become genetically specified, then these spaces must have the property of neighbourhood corr...
New single-cell recordings show that humans do have mirror neurons, and in more brain regions than previously suspected. Some action-execution neurons were seen to be inhibited during observation, possibly preventing imitation and helping self/other discrimination.
This study compares the maze learning performance of three artificial neural network architectures: an Elman recurrent neural network, a long short-term memory (LSTM) network, and Mona, a goal-seeking neural network. The mazes are networks of distinctly marked rooms randomly interconnected by doors that open probabilistically. The mazes are used to examine two important problems related to artificial neural networks: (1) the retention of long-term state information and (2) the modular use of learned information. For the former, mazes impose a context learning demand: at the beginning of the maze, an initial door choice forms a context that must be remembered until the end of the maze, where the same numbered door must be chosen again in order to reach the goal. For the latter, the effect of modular and non-modular training is examined. In modular training, the door associations are trained in separate trials from the intervening maze paths, and only presented together in testing trials. All networks performed well on mazes without the context learning requirement. The Mona and LSTM networks performed well on context learning with non-modular training; the Elman performance degraded as the task length increased. Mona also performed well for modular training; both the LSTM and Elman networks performed poorly with modular training.
Modeling natural motivations into hybrid artificial agents
- F Andriamasinoro
F. Andriamasinoro, Modeling natural motivations into hybrid
artificial agents, Fourth International ICSC Symposium on
Engineering of Intelligent Systems (EIS 2004), 2004.
Lund University Cognitive Studies
- C Balkenius
C. Balkenius, Biological Learning and Artificial Intelligence,
Lund University Cognitive Studies 30 (1994).
Maze studies with the white rat. I. Normal animals
- H A Carr
H.A. Carr, Maze studies with the white rat. I. Normal animals,
J Anim Behav 7 (1913), 259-275.
- M L Kringelbach
- K C Berridge
M.L. Kringelbach and K.C. Berridge, The Joyful Mind, Scientific American 307(2) (2012), 40-45.
- B F Skinner
B.F. Skinner, About Behaviorism, 1976, ISBN 0-394-71618-3.
Towards A Human Behavior Model Based On Instincts
- V C Hung
- A J Gonzalez
V.C. Hung and A.J. Gonzalez, Towards A Human Behavior Model Based On Instincts, 2007 Conference on Behavior
Representation in Modeling and Simulation (BRIMS), 2007.