Keyan Ghazi-Zahedi

• Dr. rer. nat.
• PostDoc Position at Max Planck Institute for Mathematics in the Sciences

There are numerous examples that show how the exploitation of the body’s physical properties can lift the burden of the brain. Examples include grasping, swimming, locomotion, and motion detection. The term Morphological Computation was originally coined to describe processes in the body that would otherwise have to be conducted by the brain. In th...

In many robotic applications, softness leads to improved performance, robustness, and safety, while lowering manufacturing cost, increasing versatility, and simplifying control. The advantages of soft robots derive from the fact that their behavior partially results from interactions of the robot's morphology with its environment, which is commonly...

Full-text can be downloaded from Frontiers in Robotics and AI: http://journal.frontiersin.org/article/10.3389/frobt.2016.00042/full open access In the context of embodied artificial intelligence, morphological computation refers to processes which are conducted by the body (and environment) that otherwise would have to be performed by the brain. E...

The field of embodied intelligence emphasises the importance of the morphology and environment with respect to the behaviour of a cognitive system. The contribution of the morphology to the behaviour, commonly known as morphological computation, is well-recognised in this community. We believe that the field would benefit from a formalisation of th...

Author Summary Given a body and an environment, what is the brain complexity needed in order to generate a desired set of behaviors? The general understanding is that the physical properties of the body and the environment correlate with the required brain complexity. More precisely, it has been pointed that naturally evolved intelligent systems te...

Citizen-generated counter speech is a promising way to fight hate speech and promote peaceful, non-polarized discourse. However, there is a lack of large-scale longitudinal studies of its effectiveness for reducing hate speech. To this end, we perform an exploratory analysis of the effectiveness of counter speech using several different macro- and...

Voluntary movements, like point-to-point or oscillatory human arm movements, are generated by the interaction of several structures. High-level neuronal circuits in the brain are responsible for planning and initiating a movement. Spinal circuits incorporate proprioceptive feedback to compensate for deviations from the desired movement. Muscle bioc...

Citizen-generated counter speech is a promising way to fight hate speech and promote peaceful, non-polarized discourse. However, there is a lack of large-scale longitudinal studies of its effectiveness for reducing hate speech. We investigate the effectiveness of counter speech using several different macro- and micro-level measures of over 180,000...

Hateful rhetoric is plaguing online discourse, fostering extreme societal movements and possibly giving rise to real-world violence. A potential solution to this growing global problem is citizen-generated counter speech where citizens actively engage in hate-filled conversations to attempt to restore civil non-polarized discourse. However, its act...

Intelligence results from the interaction of the brain, body and environment. The question addressed in this book is, can we measure the contribution of the body and its' interaction with the environment? To answer this, we first present a comprehensive overview of the various ways in which a body reduces the amount of computation that the brain h...

Information theory is the foundation for most of the quantifications that are discussed in this book. This chapter presents fundamental information theoretic concepts, including entropy, mutual information, and conditional mutual information. An important aspect is how these measure can be estimated from discrete and continuous data. Finally, this...

The previous chapter introduced and discussed five different concepts to quantify morphological intelligence. The goal of this chapter is to investigate how the majority of these measures perform for different configurations of the sensorimotor loop. This means that we want to investigate how the measures perform, e.g. if the behaviour of the syste...

In this work, we are not focussing only on a formal treatment, but also interested in the applicability of the measures on real data. From this type of analysis, it seems that \(\mathrm {MI}_\mathrm {W}\), so far, is one of the best-suited candidates for applications. This was independently confirmed in previous publications [1-3]. This chapter pre...

When I feel thirsty, I grasp a glass of water and move it to my mouth without thinking about the exact size and material properties of the glass. When I run through the woods, I can relax my mind, because I don’t have to concentrate on the ground that I am running on. The question that motivates this book is: How is this possible? Why don’t I have...

Pfeifer and Iida [1] and Paul [2] state that “One problem with the concept of morphological computation is that while intuitively plausible, it has defied serious quantification efforts.” Paul [2] adds “We would like to be able to ask: How much computation is actually being done?” In the context of this work, we would rephrase this question in the...

The behavior of living systems is based on the experience they gained through their interactions with the environment [1]. This experience is stored in the complex biochemical networks of cells and organisms to provide a relationship between a sensed situation and what to do in this situation [2-4]. An implementation of such processes in artificial...

World record setting has long attracted public interest and scientific investigation. Extremal records summarize the limits of the space explored by a process, and the historical progression of a record sheds light on the underlying dynamics of the process. Existing analyses of prediction, statistical properties, and ultimate limits of record progr...

Modularisation, repetition, and symmetry are structural features shared by almost all biological neural networks. These features are very unlikely to be found by the means of structural evolution of artificial neural networks. This paper introduces NMODE, which is specifically designed to operate on neuro-modules. NMODE addresses a second problem i...

Reinforcement learning for embodied agents is a challenging problem. The accumulated reward to be optimized is often a very rugged function, and gradient methods are impaired by many local optimizers. We demonstrate, in an experimental setting, that incorporating an intrinsic reward can smoothen the optimization landscape while preserving the globa...

Conditional restricted Boltzmann machines are undirected stochastic neural networks with a layer of input and output units connected bipartitely to a layer of hidden units. These networks define models of conditional probability distributions on the states of the output units given the states of the input units, parameterized by interaction weights...

It is well known that for any finite state Markov decision process (MDP) there is a memoryless deterministic policy that maximizes the expected reward. For partially observable Markov decision processes (POMDPs), optimal memoryless policies are generally stochastic. We study the expected reward optimization problem over the set of memoryless stocha...

The question how an agent is affected by its embodiment has attracted growing attention in recent years. A new field of artificial intelligence has emerged, which is based on the idea that intelligence cannot be understood without taking into account embodiment. We believe that a formal approach to quantifying the embodiment's effect on the agent's...

In recent years, the application of information theory to the field of embodied intelligence has turned out to be extremely fruitful. Here, several measures of information flow through the sensorimotor loop of an agent are of particular interest. There are mainly two ways to apply information theory to the sensorimotor setting.

One of the main challenges in the field of embodied artificial intelligence is the open-ended autonomous learning of complex behaviors. Our approach is to use task-independent, information-driven intrinsic motivation(s) to support task-dependent learning. The work presented here is a preliminary step in which we investigate the predictive informati...

This article deals with the causal structure of an agent’s sensori-motor loop and its relation to deliberative decision making. Of particular interest are causal effects that can be identified from an agent-centric perspective based on in situ observations. Within this identification, an optimal world model of the agent plays a central role. Its op...

This work presents a novel learning method in the context of embodied artificial intelligence and self-organization, which has as few assumptions and restrictions as possible about the world and the underlying model. The learning rule is derived from the principle of maximizing the predictive information in the sensorimotor loop. It is evaluated on...

This paper presents YARS (Yet Another Robot Simulator), which was initially developed in the context of evolutionary robotics (ER), yet includes features which are also of benefit to those outside of this field. An experiment in YARS is defined by a single XML file, which includes the simulator configuration, the (randomisable) environment, and any...

This paper presents a modular neural network controller for fast locomotion of a quadruped robot. It was generated by artificial evolution techniques using a physical simulation of the Sony Aibo ERS-7. Co-evolution was used to develop neuromodules controlling the single legs as well as the coordination between the four legs. The final neurocontroll...

It is claimed that synaptic plasticity of neural controllers for autonomous robots can enhance the behavioral properties of these systems. Based on homeostatic properties of so called self-regulating neurons, the presented mechanism will vary the synaptic strength during the robot interaction with the environment, due to driving sensor inputs and m...

Robot intelligence is often associated with the concept of autonomous systems which have to decide and act without central control, external technical guidances, or human assistance. Especially autonomous mobile robots are nowadays conceived of as robots that can operate in complex, dynamically non-trivial environments. They are supposed to be equi...

In our view walking machines is not a goal in itself. Of course, on one hand there are interesting applications, especially for exploration tasks, but on the other hand, a walking robot serves as demonstrator for nonlinear and adaptive control tasks with a high number of degrees-of-freedom and fast-changing sensor inputs. Here we describe a modular...

Using discrete-time dynamics of a two neuron network with recurrent connectivity it is shown that for specic parameter congura- tions the output signals of neurons can be of almost sinusoidal shape. These networks live near the Sacker-Neimark bifurcation set, and are termed SO(2)-networks, because their weight matrices correspond to ro- tations in...

Small recurrent neural network with two and three neurons are able to control autonomous robots showing obstacle avoidance and photo-tropic behaviors. They have been generated by evolutionary pro- cesses, and they demonstrate, how dynamical properties can be used for an effective behavior control. Presented examples also show how sensor fusion can...

This article presents a method, which enables an autonomous mo- bile robot to create an internal representation of the external world. The elements of this internal representation are the dynamical features of a neuro-controller and their time regime during the interaction of the robot with its environment. As an examples of this method the be- hav...

Even if the character of robotics is primarily technological, it was always closely connected with biology right from the beginning. However, most of the time this was only a one-way relationship, for biological insights were often used as a pool of approved ideas and methods to find solutions for rudimentary problems in robotics (walking machines...

Even if the character of robotics is primarily technological, it was always closely connected with biology right from the beginning. However, most of the time this was only a one-way relationship, for biological insights were often used as a pool of approved ideas and methods to find solutions for rudimentary problems in robotics (walking machines...

Abstract In this paper we present the hard and software architec ture of the robots of the T Team Tuebingen which participated in the RoboCup This paper describes how we try to accomplish the basic skills of our robot team capable of successfully playing robot soccer by designing our hard and software and the experiences we made with our team at th...

Introduction The dynamical system approach to natural cognitive systems is formulated as an empirical hypothesis, that can only be validated "if in a long run, the best theories of cognitive processes are expressed in dynamical terms.'' 1 From this point of view scientists emphasize the importance of concrete examples of minimal cognitive systems d...