A View on the Nature of Consciousness

In the process of communicating with other bloggers that are interested in the future of humanity and philosophy of mind, some upcoming discussions have been planned on a number of related topics. The first topic is: the nature of consciousness and its relationship to the prospect of artificial intelligence. In preparation for the discussion, I’ve summarised my position on this topic here. I’ve spent some time reading and thinking about the nature of consciousness, so I believe that my position has some firm evidence and logical reasoning supporting it. If requested, I’ll follow up with post(s) and comment(s) providing more detailed descriptions of the steps of reasoning and evidence. As always, I’m open to considering compelling evidence and arguments that refute the points below.

The Nature of Consciousness

1. Consciousness can be defined as its ‘nature’. We seem to define consciousness by trying to describe our experience of it and how others show signs of consciousness or lack of consciousness. If we can successfully explain how consciousness occurs — its nature — we could then use that explanation as a definition. Nevertheless, for now we might use a broad dictionary definition of consciousness, such as “the awareness of internal (mental) and external (sensory) states”.

2. Consciousness is a spectrum. Something may be considered minimally consciousness if its only “aware” of external-sensory states. Higher consciousness includes awareness of internal-mental states, such as conscious thoughts and access to memories. Few animals, even insects, appear to be without “awareness” of memory (particularly spatial memory). As we examine animals of increasing intelligence we typically see a growing sets of perceptual and cognitive abilities — growing complexity in the range of awareness — though varying proficiencies at these abilities.

3. Biological consciousness is the result of physical processes in the brain. Perception and cognition are the result of the activity of localised, though not independent, functional groups of neurons. We can observe a gross relationship between brain structure and cognitive and perceptual abilities by studying structural brain differences animal species of various perceptual and cognitive abilities. With modern technology, and lesion studies, we can observe precise correlations between brain structures, and those cognitive and perceptual processes.

4. The brain is composed of causal structures. The collection of functional groups of neurons in the entire body (peripheral and central nervous system) are interdependent causal systems — at any moment neurons operate according to definable rules, effected by only the past and present states of themselves, their neighbours and surroundings.

5. Causal operation produces representation and meaning. Activity in groups of neurons have the power to abstractly represent information. Neural activity has “meaning” due to being the result of the chain of interactions that typically stretch back to some sensory interaction or memory. The meaning is most clear when neural activity represents external interactions with sensory neurons, e.g., a neuron in the primary visual cortex might encode for an edge of a certain orientation in a particular part of the visual field. There is also evidence for the existence of “grandmother cells”: neurons, typically in the temporal lobe of the neocortex, that activates almost exclusively in response to a very specific concept, such as “Angelina Jolie” (both a picture of the actress and her name).

6. Consciousness is an emergent phenomenon.  Consciousness is (emerges from) the interaction and manipulation of representations, which in biological organisms is performed by the structure of the complete nervous system and developed neural activity. Qualia are representations of primitive sensory interactions and responses. For example, the interaction of light hitting the photosensitive cells in the retina ends up represented as the activation of neurons in the visual cortex. It is potentially possible to have damage to the visual cortex and lose conscious awareness of light (though sometimes still be capable of blindsight). Physiological responses can result from chemicals and neural activity and represent emotions.

7. Consciousness would emerge from any functionally equivalent physical system. Any system that produces the interaction and manipulation of representations will, as a result, produce some form of consciousness. From a functional perspective, a perfect model of neurons, synapses and ambient conditions is not likely to be required to produce representations and interactions. Nevertheless, even if a perfect model of the brain was necessary (down to the atom), the brain and its processes, however complex, function within the physical laws (most likely even classical physics). The principle of universal computation would allow its simulation (given a powerful enough computer) and this simulation would fulfil the criteria above for being conscious.

8. Strong artificial intelligence is possible and would be conscious. Human-like artificial intelligence requires the development of human-equivalent interdependent modules for sensory interaction and perceptual and cognitive processing that manipulate representations. This is theoretically possible in software. The internal representations this artificial intelligence would possess, with processes for interaction and manipulation, would generate qualia and human-like consciousness.

Philosophical Labels

I’ve spent some time reading into various positions within the philosophy of mind, but I’m still not entirely sure where these views fit. I think there are close connections to:

a) Physicalism: I don’t believe there is anything other than that which is describable by physics. That doesn’t mean, however, that there aren’t things that have yet to be adequately described by physics. For example, I’m not aware of an adequate scientific description of the relationship between causation, representation and interpretation — which I think are possibly the most important elements in consciousness. Nevertheless, scientific progress should continue to expand our understanding of the universe.

b) Reductionism and Emergentism: I think things are the sum of their parts (and interactions), but that reducing them to the simplest components is rarely the best way to understand a system. It is, at times, possible to make very accurate, and relatively simple, mathematical models to describe the properties and functionality of complex systems. Finding the right level of description is important in trying to understand the nature of consciousness — finding adequate models of neuronal representations and interactions.

c) Functionalism: These views seem to be consistent with functionalism — consciousness is dependent on the function of the underlying structure of the nervous system. Anything that reproduces the function of a nervous system would also reproduce the emergent property of consciousness. For example, I think the ‘China brain’ would be conscious and experience qualia — it is no more absurd than the neurons in our brain being physically isolated cells that communicate to give rise to the experience of qualia.

Changing Views

I’m open to changing these views in light of sufficiently compelling arguments and evidence. I have incomplete knowledge, and probably some erroneous beliefs; however, I have spent long enough studying artificial intelligence, neuroscience and philosophy to have some confidence in this answer to “What is the nature of consciousness and its relationship to the prospect of artificial intelligence?”.

Please feel free to raise questions or arguments against anything in this post. I’m here to learn, and I will respond to any reasonable comments.

State space: Quantities and qualities

GridWorldThis is the second post in a series on rewards and values, the previous post discussed whether rewards are external stimuli or internal brain activity. This post discusses the important issue of representing the world in a computer or robot, and the practice of describing the world as discrete quantities or abstract qualities.

The world we live in can usually be described as being in a particular state, e.g., the sky is cloudy, the door is closed, the car is travelling at 42km/h. To be absolutely precise about the state of the world we need to use quantities and measurements: position, weight, number, volume, and so on. But how often do we people know the precise quantitative state of the world we live in? Animals and people often get by without quantifying the exact conditions of the world around them, instead perceiving the qualities of the world – recognising and categorising things, and making relative judgements about position, weight, speed, etc. But then why are robots often programmed to use quantitative descriptions of the world rather than qualitative descriptions? This is a complex issue that won’t be comprehensively answered in this post, but some differences in computer-based representation with quantities and with qualities will be described.

For robots, the world can be represented as a state space. When dealing with measurable quantities the state space often divides up the world into partitions. A classic example in reinforcement learning is navigating a “gridworld“. In the gridworld, the environment the agent finds itself is literally a square grid, and the agent can only move in the four compass directions (north, south, east and west). In the computer these actions and states would usually represented as numbers: state 1, state 2, …, state n, and action 1, action 2, …, action m. The “curse of dimesionality” appears because to store the value of every state-action pair the number of states multiplied by the number of actions. If we add another dimension to the environment with another k possible values, our number of states is multiplied by k. A ten by ten grid, with another dimension of 10 values goes from having 100 states to 1000 states. With four different movements available the agent has 4 actions, so there would be 4000 state-action pairs.

While this highlights one serious problem of representing the world quantitatively, an equally serious problem is deciding how fine should our quantity divisions be? If the agent is a mobile robot driving around a laboratory with only square obstacles, we could probably get by dividing the world up into 50cm x 50cm squares. But if the robot was required to pick something up from a tabletop, it might need to has accuracy down to the centimetre. If it drives around the lab as well as picking things up from tabletops, dividing up the world gets trickier. The grid that makes up the world can’t just describe occupancy, areas of the grid occupied by objects of interest need to be specified as those objects, adding more state dimensions to the representation.

When we people make a choice to do something, like walk to the door, we don’t typically update that choice each time we move 50cm. We collapse all the steps along the way into a single action. Hierarchical reinforcement learning does just this, with algorithms coming under this banner collecting low level actions into high level actions, hierarchically. One popular framework collects actions into “options”, a method of selecting actions (e.g., ‘go north’ 100 times) and evaluating end-conditions (e.g., hit a wall or run out of time) that allow for a reduction in the number of times an agent needs to make a choice (e.g., choose ‘go north’ 100 times) to see how things pan out. This simplifies the process of choosing actions that the agent performs, but it doesn’t simplify the representation of the environment.

When we look around we see the objects – right now you are looking at some sort of computer screen – we also see objects that make up any room we’re in: the door, the floor, the walls, tables and chairs. In our minds, we would seem to represent the world around us as a combined visual and spatial collection of objects. Describing the things in the world as the objects they are in the minds of people allows our “unit of representation” to be any size, and can dramatically simplify the way the world is described. And that is what is happening in more recent developments in machine learning, specifically with relational reinforcement learning and object-oriented reinforcement learning.

In relational reinforcement learning, things in the world are described by their relationship to other things. For example, the coffee cup is on the table and the coffee is in the coffee cup. These relations can usually be described using simple logic statements. Similar to relational abstraction of the world, object-oriented reinforcement learning allows objects to have properties and have associated actions, much like classes in object-oriented programming. Given that object-oriented programming was designed partly because it was related to how we people describe the world, viewing the world as objects has a lot of conceptual benefits. The agent considers the state of objects and learns the effects of actions with those objects. In the case of a robot, we reduce the problem of having large non-meaningful state spaces, but then run into the challenge of recognising objects – a serious hurdled in the world of robotics that isn’t yet solved.

A historical reason for ‘why were quantitative divisions for state space used in the first place?’ is because some problems, such as balancing a broom or gathering momentum to get up a slope, were designed to use as little prior information and as little sensory feedback as possible. This challenge turned into how to get a system to efficiently learn to solve these problems when having to blindly search for a reward or avoid a punishment. Generally speaking, many of the tasks requiring the discrete division of a continuous range are ones that involve some sort of motor control. The same sort of tasks that people perform using vision and touch to provide much more detailed feedback than plain success or failure. The same sort of tasks that we couldn’t feel our success or failure unless we could sense what was happening and had hard-wired responses or some goal in mind (or had someone watching to give feedback). This might mean that reinforcement learning is really the wrong tool for learning low-level motor control, unless that is, we don’t care to give our robots eyes.

This leads me to the topic of the next post in this series on rewards and values: “Self-rewarding autonomous machines“. I’ll discuss how a completely autonomous machine will need to have perceptual capabilities of detecting “good” and “bad” events and reward themselves. I’ll also discuss how viewing the world as “objects” that drive actions will lead to a natural analogy with how animals and people function in the world.