Publications by Simon D. Levy (* indicates student co-author)


By way of dealing with the creation of an intelligent machine named Ava, the movie Ex Machina (Alex Garland, 2014) engages profoundly and seriously with fundamental issues like personhood: the very question of what it means to be human—but it can also be seen as a dark comedy bedroom farce. In this paper, we attempt a synthesis of these two views. The crux of our argument is that what is revealed by Ex Machina is that the notion of consciousness currently promoted is not only peripheral, but antithetical, to understanding what artificial intelligence (AI) and robotics are really about. Using Ludwig Wittgenstein’s insights, we attempt to show what is misleading about testing a machine for consciousness, what is helpful in trying to get a machine to model human thought, and how the games we choose to play with machines can either be vicariously dehumanizing or can encourage an empathetic extension of language.

  • Levy, S.D. (2020) A Simple Platform for Reinforcement Learning of Simulated Flight Behaviors.  Proceedings of Living Machines 2020 (Lecture Notes in Computer Science), Springer Verlag.

We present work-in-progress on a novel, open-source software platform supporting Deep Reinforcement Learning (DRL) of flight behaviors for Miniature Aerial Vehicles (MAVs). By using a physically realistic model of flight dynamics and a simple simulator for high-frequency visual events, our platform avoids some of the shortcomings associated with traditional MAV simulators. Implemented as an OpenAI Gym environment, our simulator makes it easy to investigate the use of DRL for acquiring common behaviors like hovering and predation. We present preliminary experimental results on two such tasks, and discuss our current research directions. Our code, available as a public github repository, enables replication of our results on ordinary computer hardware.


  • Levy, S.D. (2020) Robustness Through Simplicity: A Minimalist Gateway to Neurorobotic Flight. Frontiers in Neurorobotics, 16 March 2020.

In attempting to build neurorobotic systems based on flying animals, engineers have come to rely on existing firmware and simulation tools  designed for miniature aerial vehicles (MAVs). Although they provide a valuable platform for the collection of data for Deep Learning and related AI approaches, such tools are deliberately designed to be general (supporting air, ground, and water vehicles) and feature-rich. The sheer amount of code required to support such broad capabilities can make it a daunting task to adapt these tools to building neurorobotic systems for flight. In this paper we present a complementary pair of simple, object-oriented software tools (multirotor flight-control firmware and simulation platform), each consisting of a core of a few thousand lines lines of C++ code, that we offer as a candidate solution to this challenge. By providing a minimalist application programming interface (API) for sensors and PID controllers, our software tools make it relatively painless to for engineers
to prototype neuromorphic approaches to MAV sensing and navigation. We conclude our discussion by presenting a simple PID controller we built using the popular Nengo neural simulator in conjunction with our flight-simulation platform.

By pointing out deep philosophical confusions endemic to cognitive science, Wittgenstein might seem an enemy of computational approaches. We agree (with Mills 1993) that while Wittgenstein would reject the classicist’s symbols and rules approach, his observations align well with connectionism. While many connectionisms that dominated the later 20th century could still fall prey to criticisms of biological, pedagogical, and linguistic implausibility, current connectionist approaches can resolve those problems in a Wittgenstein-friendly manner. We (a) present the basics of a Vector Symbolic Architecture formalism, inspired by Smolensky (1990), and indicate how high-dimensional vectors can operate in a context-sensitive and object-independent manner in biologically plausible time scales, reflecting Wittgenstein’s notions of language-games and family resemblance; we (b) show how “soft” symbols for such a formalism can be formed with plausible learning cycles using Sparse Distributed Memory, which can resolve disputes surrounding Wittgenstein’s private language argument; and (c) show how connectionist networks can extrapolate meaningful patterns to solve problems, providing “ways to go on” without explicit rules, which indicates linguistic plausibility. Connectionism thus provides a systematicity and productivity that is more than a mere implementation of a classical approach, and provides Wittgenstein-friendly and even Wittgenstein-illuminating models of mind and language for cognitive science.

  • Wilkinson, C.*, D. Harbor, T. Keel*, S. Levy, and J. Kuehner (2016) Sensing fluid pressure during plucking events in a natural bedrock channel and experimental flume

Abstract accepted for poster presentation at AGU 2016.

  • Kaplan, D. T., S.D. Levy, and K.A. Lambert (2016) Introduction to Scientific Computation and Programming in Python. Project Mosaic Books.

This book provides students with the modern skills and concepts needed to be able to use a computer expressively in scientific work. The authors take an integrated approach by covering programming, important methods and techniques of scientific computation (graphics, the organization of data, data acquisition, numerical issues, etc.) and the organization of software. Balancing the best of the teach-a-package and teach-a-language approaches, the book teaches general-purpose language skills and concepts, and also takes advantage of existing package-like software so that realistic computations can be performed.

Buy on Project Mosaic Books      Buy on Amazon

  • Levy, S.D., C. Lowney, W. Meroney, and R.W. Gayler (2014) Bracketing the Beetle: How Wittgenstein’s Understanding of Language Can Guide Our Practice in AGI and Cognitive Science. In B. Goertzel el al. (Eds.) Proceedings of the Seventh Conference on Artificial General Intelligence (Lecture Notes in Compute Science 8598, Springer-Verlag).

We advocate for a novel connectionist modeling framework as an answer to a set of challenges to AGI and cognitive science put forth by classical formal systems approaches. We show how this framework, which we call Vector Symbolic Architectures, or VSAs, is also the kind of model of mental activity that we arrive at by taking Ludwig Wittgenstein’s critiques of the philosophy of mind and language seriously. We conclude by describing how VSA and related architectures provide a compelling solution to three central problems raised by Wittgenstein in the Philosophical Investigations regarding rule-following, aspect-seeing, and the development of a “private” language.

Paper   Software  BibTex

  • Levy, S.D., S. Bajracharya*, and R.W. Gayler (2013) Learning Behavior Hierarchies via High-Dimensional Sensor Projection. In Learning Rich Representations from Low-Level Sensors: Papers from the 2013 AAAI Workshop.

We propose a knowledge-representation architecture allowing a robot to learn arbitrarily complex, hierarchical / symbolic relationships between sensors and actuators. These relationships are encoded in high-dimensional, low-precision vectors that are very robust to noise. Low-dimensional (single-bit) sensor values are projected onto the high-dimensional representation space using low-precision random weights, and the appropriate actions are then computed using elementwise vector multiplication in this space. The high-dimensional action representations are then projected back down to low-dimensional actuator signals via a simple vector operation like dot product. As a proof-of-concept for our architecture, we use it to implement a behavior-based controller for a simulated robot with three sensors (touch sensor, left/right light sensor) and two actuators (wheels). We conclude by discussing the prospects for deriving such representations automatically.

Paper   Software  BibTex

  • Gayler, R.W. and S. D. Levy, eds. (2011) Compositional Connectionism in Cognitive Science II: The Localist / Distributed DimensionConnection Science 23:2.Abstract

The aim of this workshop was to bring together researchers working with a wide range of compositional connectionist models, independent of application domain (e.g. language, logic, analogy, web search), with a focus on what commitments (if any) each model makes to localist or distributed representation. We solicited submissions from both localist and distributed modellers, as well as those whose work bypasses this distinction or challenges its importance. We expected vigorous and exciting debate on this topic, and we were not disappointed. Specifically, our call for participation encouraged discussion on the following topics:

  1. What do we mean by ‘localist’/’distributed’ in terms of the relationship between connectionist units and the items they represent?
  2. How plausible and feasible is ‘holistic’ computation, in which an entire structure is manipulated with sensitivity to its constituent parts without being decomposed into those parts? Does this feasibility depend on whether the representation is localist/distributed?
  3. What constraints can neuroscience research bring to the distributed/localist debate? What can this debate contribute to the interpretation of neuroscientific research?
  4. Are some cognitive functions more plausibly seen as localist, and others more plausibly distributed?
  5. Do distributed (or localist) models scale more easily than localist (or distributed) models to realistically large problems?

Author Posting. © Taylor & Francis, 2011. This is the authors’ version of the work. It is posted here by permission of Taylor & Francis for personal use, not for redistribution. The definitive version was published in Connection Science, Volume 23 Issue 2, June 2011.doi:10.1080/09540091.2011.587505BibTex

  • Gayler, R.W., S.D. Levy, and R. Bod (2010) Explanatory Aspirations and the Scandal of Cognitive Neuroscience. Proceedings of Biologically Inspired Cognitive Architectures 2010. ISO Press.


    In this position paper we argue that brain-inspired cognitive architectures must simultaneously be compatible with the explanation of human cognition and support the human design of artificial cognitive systems. Most

Most cognitive neuroscience models fail to provide a basis for implementation because they neglect necessary levels of functional organisation in jumping directly from physical phenomena to cognitive behaviour. Of those models that do attempt to include the intervening levels, most either fail to implement the required cognitive functionality or do not scale adequately. We argue that these problems of functionality and scaling arise because of identifying computational entities with physical resources such as neurons and synapses. This issue can be avoided by introducing appropriate virtual machines. We propose a tool stack that introduces such virtual machines and supports design of cognitive architectures by simplifying the design task through vertical modularity.