Hard problem of consciousness

Summary

The hard problem of consciousness is a philosophical problem concerning why and how humans and other organisms have qualia, phenomenal consciousness, or subjective experiences. This is in contrast to the "easy problems" of explaining the physical systems that give humans and other animals the ability to discriminate, integrate information, perform behavioural functions, or provide behavioural reports, and so forth. The easy problems are considered "easy" not because they are literally easy, but because they are problems that are in principle amenable to functional explanations: that is, explanations that are mechanistic or behavioural, as they can be explained (at least in principle) purely by reference to the "structure and dynamics" that underpin the phenomenon in question. Proponents of the hard problem argue that conscious experience is categorically differ

Official source

https://en.wikipedia.org/wiki/Hard_problem_of_consciousness

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related publications (16)

Related publications

Related people (1)

Related people

Related units (1)

Related units

Related concepts (20)

Related concepts

Related courses (8)

Related courses

Related lectures (13)

Related lectures

CauseOccam: Learning Interpretable Abstract Representations in Reinforcement Learning Environments via Model Sparsity

Sergei Volodin

"I choose this restaurant because they have vegan sandwiches" could be a typical explanation we would expect from a human. However, current Reinforcement Learning (RL) techniques are not able to provide such explanations, when trained on raw pixels. RL algorithms for state-of-the-art benchmark environments are based on neural networks, which lack interpretability, because of the very factor that makes them so versatile – they have many parameters and intermediate representations. Enforcing safety guarantees is important when deploying RL agents in the real world, and guarantees require interpretability of the agent. Humans use short explanations that capture only the essential parts and often contain few causes to explain an effect. In our thesis, we address the problem of making RL agents understandable by humans. In addition to the safety concerns, the quest to mimic human-like reasoning is of general scientific interest, as it sheds light on the easy problem of consciousness. The problem of providing interpretable and simple causal explanations of agent's behavior is connected to the problem of learning good state representations. If we lack such a representation, any reasoning algorithm's outputs would be useless for interpretability, since even the "referents" of the "thoughts" of such a system would be obscure to us. One way to define simplicity of causal explanations via the sparsity of the Causal Model that describes the environment: the causal graph has the fewest edges connecting causes to their effects. For example, a model for choosing the restaurant that only depends on the cause "vegan" is simpler and more interpretable than a model that looks at each pixel of a photo of the menu of a restaurant, and possibly relies as well on spurious correlations, such the style of the menu. In this thesis, we propose a framework "CauseOccam" for model-based Reinforcement Learning where the model is regularized for simplicity in terms of sparsity of the causal graph it corresponds to. The framework contains a learned mapping from observations to latent features, and a model predicting latent features at the next time-steps given ones from the current time-step. The latent features are regularized with the sparsity of the model, compared to a more traditional regularization on the features themselves, or via a hand-crafted interpretability loss. To achieve sparsity, we use discrete Bernoulli variables with gradient estimation, and to find the best parameters, we use the primal-dual constrained formulation to achieve a target model quality. The novelty of this work is in learning jointly a sparse causal graph and the representation taking pixels as the input on RL environments. We test this framework on benchmark environments with non-trivial high-dimensional dynamics and show that it can uncover the causal graph with the fewest edges in the latent space. We describe the implications of our work for developing priors enforcing interpretability.

2021

Optimization is a fundamental tool in modern science. Numerous important tasks in biology, economy, physics and computer science can be cast as optimization problems. Consider the example of machine learning: recent advances have shown that even the most sophisticated tasks involving decision making, can be reduced to solving certain optimization problems. These advances however, bring several new challenges to the field of algorithm design. The first of them is related to the ever-growing size of instances, these optimization problems need to be solved for. In practice, this forces the algorithms for these problems to run in time linear or nearly linear in their input size. The second challenge is related to the emergence of new, harder and harder problems which need to be dealt with. These problems are in most cases considered computationally intractable because of complexity barriers such as NP completeness, or because of non-convexity. Therefore, efficiently computable relaxations for these problems are typically desired. The material of this thesis is divided into two parts. In the first part we attempt to address the first challenge. The recent tremendous progress in developing fast algorithm for such fundamental problems as maximum flow or linear programming, demonstrate the power of continuous techniques and tools such as electrical flows, fast Laplacian solvers and interior point methods. In this thesis we study new algorithms of this type based on continuous dynamical systems inspired by the study of a slime mold Physarum polycephalum. We perform a rigorous mathematical analysis of these dynamical systems and extract from them new, fast algorithms for problems such as minimum cost flow, linear programming and basis pursuit. In the second part of the thesis we develop new tools to approach the second challenge. Towards this, we study a very general form of discrete optimization problems and its extension to sampling and counting, capturing a host of important problems such as counting matchings in graphs, computing permanents of matrices or sampling from constrained determinantal point processes. We present a very general framework, based on polynomials, for dealing with these problems computationally. It is based, roughly, on encoding the problem structure in a multivariate polynomial and then recovering the solution by means of certain continuous relaxations. This leads to several questions on how to reason about such relaxations and how to compute them. We resolve them by relating certain analytic properties of the arising polynomials, such as the location of their roots or convexity, to the combinatorial structure of the underlying problem. We believe that the ideas and mathematical techniques developed in this thesis are only a beginning and they will inspire more work on the use of dynamical systems and polynomials in the design of fast algorithms.

EPFL2018

Design and Validation of a Modular One-To-Many Actuator for a Soft Wearable Exosuit

Silvestro Micera, Michele Xiloyannis

The size, weight, and power consumption of soft wearable robots rapidly scale with their number of active degrees of freedom. While various underactuation strategies have been proposed, most of them impose hard constrains on the kinetics and kinematics of the device. Here we propose a paradigm to independently control multiple degrees of freedom using a set of modular components, all tapping power from a single motor. Each module consists of three electromagnetic clutches, controlled to convert a constant unidirectional motion in an arbitrary output trajectory. We detail the design and functioning principle of each module and propose an approach to control the velocity and position of its output. The device is characterized in free space and under loading conditions. Finally, we test the performance of the proposed actuation scheme to drive a soft exosuit for the elbow joint, comparing it with the performance obtained using a traditional DC motor and an unpowered-exosuit condition. The exosuit powered by our novel scheme reduces the biological torque required to move by an average of 46.2%, compared to the unpowered condition, but negatively affects movement smoothness. When compared to a DC motor, using the our paradigm slightly deteriorates performance. Despite the technical limitations of the current design, the method proposed in this paper is a promising way to design more portable wearable robots.

FRONTIERS MEDIA SA2019

CauseOccam: Learning Interpretable Abstract Representations in Reinforcement Learning Environments via Model Sparsity

Sergei Volodin

2021

EPFL2018