This article explores analogism and creativity, starting with a detailed investigation into IQ-test style analogy problems and how both the brain and some new artificial neural networks solve them. Next we analyze concept map formation in the cortex and the role of the hippocampal complex in establishing novel semantic connections: the neural basis of creative insights. From there we move into learning strategies, and finally conclude with speculations on how a grounded understanding of analogical creative reasoning could be applied towards advancing the art of rationality.
- Introduction
- Under the Hood
- Conceptual Abstractions and Cortical Maps
- The Hippocampal Association Engine
- Cultivate memetic heterogeneity and heterozygosity
- Construct and maintain clean conceptual taxonomies
- Conclusion
Introduction
The computer is like a bicycle for the mind.
-- Steve Jobs
The kingdom of heaven is like a mustard seed, the smallest of all seeds, but when it falls on prepared soil, it produces a large plant and becomes a shelter for the birds of the sky.
-- Jesus
Sigmoidal neural networks are like multi-layered logistic regression.
-- various
The threat of superintelligence is like a tribe of sparrows who find a large egg to hatch and raise. It grows up into a great owl which devours them all.
-- Nick Bostrom (see this video)
Analogical reasoning is one of the key foundational mechanisms underlying human intelligence, and perhaps a key missing ingredient in machine intelligence. For some - such as Douglas Hofstadter - analogy is the essence of cognition itself.[1]
Steve Job's bicycle analogy is clever because it encapsulates the whole cybernetic idea of computers as extensions of the nervous system into a single memorable sentence using everyday terms.
A large chunk of Jesus's known sayings are parables about the 'Kingdom of Heaven': a complex enigmatic concept that he explains indirectly through various analogies, of which the mustard seed is perhaps the most memorable. It conveys the notions of exponential/sigmoidal growth of ideas and social movements (see also the Parable of the Leaven), while also hinting at greater future purpose.
In a number of fields, including the technical, analogical reasoning is key to creativity: most new insights come from establishing mappings between or with concepts from other fields or domains, or from generalizing existing insights/concepts (which is closely related). These abilities all depend on deep, wide, and well organized internal conceptual maps.
In a previous post, I presented a high level working hypothesis of the brain as a biological implementation of a universal learning machine, using various familiar computational concepts as analogies to explain brain subsystems. In my last post, I used the conceptions of unfriendly superintelligence and value alignment as analogies for market mechanism design and the healthcare problem (and vice versa).
A clever analogy is like a sophisticated conceptual compressor that helps maximize knowledge transmission. Coming up with good novel analogies is hard because it requires compressing a complex large body of knowledge into a succinct message that heavily exploits the recipient's existing knowledgebase. Due to the deep connections between compression, inference, intelligence and creativity, a deeper investigation of analogical reasoning is useful from a variety of angles.
It is the hard task of coming up with novel analogical connections that can lead to creative insights, but to understand that process we should start first with the mechanics of recognition.
Under the Hood
You can think of the development of IQ tests as a search for simple tests which have high predictive power for g-factor in humans, while being relatively insensitive to specific domain knowledge. That search process resulted in a number of problem categories, many of which are based on verbal and mathematical analogies.
The image to the right is an example of a simple geometric analogy problem. As an experiment, start a timer before having a go at it. For bonus points, attempt to introspect on your mental algorithm.
Solving this problem requires first reducing the images to simpler compact abstract representations. The first rows of images then become something like sentences describing relations or constraints (Z is to ? as A is to B and C is to D). The solution to the query sentence can then be found by finding the image which best satisfies the likely analogous relations.
Imagine watching a human subject (such as your previous self) solve this problem while hooked up to a future high resolution brain imaging device. Viewed in slow motion, you would see the subject move their eyes from location to location through a series of saccades, while various vectors or mental variable maps flowed through their brain modules. Each fixation lasts about 300ms[2], which gives enough time for one complete feedforward pass through the dorsal vision stream and perhaps one backwards sweep.
The output of the dorsal stream in inferior temporal cortex (TE on the bottom) results in abstract encodings which end up in working memory buffers in prefrontal cortex. From there some sort of learned 'mental program' implements the actual analogy evaluations, probably involving several more steps in PFC, cingulate cortex, and various other cortical modules (coordinated by the Basal Ganglia and PFC). Meanwhile the eye frontal fields and various related modules are computing the next saccade decision every 300ms or so.
If we assume that visual parsing requires one fixation on each object and 50ms saccades, this suggests that solving this problem would take a typical brain a minimum of about 4 seconds (and much longer on average). The minimum estimate assumes - probably unrealistically - that the subject can perform the analogy checks or mental rotations near instantly without any backtracking to help prime working memory. Of course faster times are also theoretically possible - but not dramatically faster.
These types of visual analogy problems test a wide set of cognitive operations, which by itself can explain much of the correlation with IQ or g-factor: speed and efficiency of neural processing, working memory, module communication, etc.
However once we lay all of that aside, there remains a core dependency on the ability for conceptual abstraction. The mapping between these simple visual images and their compact internal encodings is ambiguous, as is the predictive relationship. Solving these problems requires the ability to find efficient and useful abstractions - a general pattern recognition ability which we can relate to efficient encoding, representation learning, and nonlinear dimension reduction: the very essence of learning in both man and machine[3].
The machine learning perspective can help make these connections more concrete when we look into state of the art programs for IQ tests in general and analogy problems in particular. Many of the specific problem subtypes used in IQ tests can be solved by relatively simple programs. In 2003, Sange and Dowe created a simple Perl program (less than 1000 lines of code) that can solve several specific subtypes of common IQ problems[4] - but not analogies. It scored an IQ of a little over 100, simply by excelling in a few categories and making random guesses for the remaining harder problem types. Thus its score is highly dependent on the test's particular mix of subproblems, but that is also true for humans to some extent.
The IQ test sub-problems that remain hard for computers are those that require pattern recognition combined with analogical reasoning and or inductive inference. Precise mathematical inductive inference is easier for machines, whereas humans excel at natural reasoning - inference problems involving huge numbers of variables that can only be solved by scalable approximations.
For natural language tasks, neural networks have recently been used to learn vector embeddings which map words or sentences to abstract conceptual spaces encoded as vectors (typically of dimensionality 100 to 1000). Combining word vector embeddings with some new techniques for handling multiple word senses, Wang and Gao et al just recently trained a system that can solve typical verbal reasoning problems from IQ tests (or the GRE) at upper human level - including verbal analogies[5].
The word vector embedding is learned as a component of an ANN trained via backprop on a large corpus of text data - Wikipedia. This particular model is rather complex: it combines a multi-sense word embedding, a local sliding window prediction objective, task-specific geometric objectives, and relational regularization constraints. Unlike the recent crop of general linguistic modeling RNNs, this particular system doesn't model full sentence structure or longer term dependencies - as those aren't necessary for answering these specific questions. Surprisingly all it takes to solve the verbal analogy problems typical of IQ/SAT/GRE style tests are very simple geometric operations in the word vector space - once the appropriate embedding is learned.
As a trivial example: "Uncle is to Aunt as King is to ?" literally reduces to:
Uncle + X = Aunt, King + X = ?, and thus X = Aunt-Uncle, and:
? = King + (Aunt-Uncle).
The (Aunt-Uncle) expression encapsulates the concept of 'femaleness', which can be combined with any male version of a word to get the female version. This is perhaps the simplest example, but more complex transformations build on this same principle. The embedded concept space allows for easy mixing and transforms of memetic sub-features to get new concepts.
Conceptual Abstractions and Cortical Maps
The success of these simplistic geometric transforms operating on word vector embeddings should not come as a huge surprise to one familiar with the structure of the brain. The brain is extraordinarily slow, so it must learn to solve complex problems via extremely simple and short mental programs operating on huge wide vectors. Humans (and now convolutional neural networks) can perform complex visual recognition tasks in just 10-15 individual computational steps (150 ms), or 'cortical clock cycles'. The entire program that you used to solve the earlier visual analogy problem probably took on the order of a few thousand cycles (assuming it took you a few dozen seconds). Einstein solved general relativity in - very roughly - around 10 billion low level cortical cycles.
The core principle behind word vector embeddings, convolutional neural networks, and the cortex itself is the same: learning to represent the statistical structure of the world by an efficient low complexity linear algebra program (consisting of local matrix vector products and per-element non-linearities). The local wiring structure within each cortical module is equivalent to a matrix with sparse local connectivity, optimized heavily for wiring and computation such that semantically related concepts cluster close together.
(Concept mapping the cortex, from this research page)
The image above is from the paper "A Continous Semantic Space Describes the Representation of Thousands of Object and Action Categories across the Human Brain" by Huth et al.[5] They used fMRI to record activity across the cortex while subjects watched annotated video clips, and then used that data to find out roughly what types of concepts each voxel of cortex responds to. It correctly identifies the FFA region as specializing in people-face things and the PPA as specializing in man-made objects and buildings. A limitation of the above image visualizations is that they don't show response variance or breadth, so the voxel colors are especially misleading for lower level cortical regions that represent generic local features (such as gabor edges in V1).
The power of analogical reasoning depends entirely on the formation of efficient conceptual maps that carve reality at the joints. The visual pathway learns a conceptual hierarchy that builds up objects from their parts: a series of hierarchical has-a relationships encoded in the connections between V1, V2, V4 and so on. Meanwhile the semantic clustering within individual cortical maps allows for fast computations of is-a relationships through simple local pooling filters.
An individual person can be encoded as a specific active subnetwork in the face region, and simple pooling over a local cluster of neurons across the face region can then compute the presence of a face in general. Smaller local pooling filters with more specific shapes can then compute the presence of a female or male face, and so on - all starting from the full specific feature encoding.
The pooling filter concept has been extensively studied in the lower levels of the visual system, where 'complex' cells higher up in V1 pool over 'simple' cell features: abstracting away gabor edges at specific positions to get edges OR'd over a range of positions (CNNs use this same technique to gain invariance to small local translations).
This key semantic organization principle is used throughout the cortex: is-a relations and more general abstractions/invariances are computed through fast local intramodule connections that exploit the physical semantic clustering on the cortical surface, and more complex has-a relations and arbitrary transforms (ex: mapping between an eye centered coordinate basis and a body centered coordinate basis) are computed through intermodule connections (which also exploit physical clustering).
The Hippocampal Association Engine
The Hippocampus is a tubular seahorse shaped module located in the center of the brain, to the exterior side of the central structures (basal ganglia, thalamus). It is the brain's associative database and search engine responsible for storing, retrieving, and consolidating patterns and declarative memories (those which we are consciously aware of and can verbally declare) over long time scales beyond the reach of short term memory in the cortex itself.
A human (or animal) unfortunate enough to suffer complete loss of hippocampal functionality basically loses the ability to form and consolidate new long term episodic and semantic memories. They also lose more recent memories that have not yet been consolidated down the cortical hierarchy. In rats and humans, problems in the hippocampal complex can also lead to spatial navigation impairments (forgetting current location or recent path), as the HC is used to compute and retrieve spatial map information associated with current sensory impressions (a specific instance of the HC's more general function).
In terms of module connectivity, the hippocampal complex sits on top of the cortical sensory hierarchy. It receives inputs from a number of cortical modules, largely in the nearby associative cortex, which collectively provide a summary of the recent sensory stream and overall brain state. The HC then has several sub circuits which further compress the mental summary into something like a compact key which is then sent into a hetero-auto-associative memory circuit to find suitable matches.
If a good match is found, it can then cause retrieval: reactivation of the cortical subnetworks that originally formed the memory. As the hippocampus can't know for sure which memories will be useful in the future, it tends to store everything with emphasis on the recent, perhaps as a sort of slow exponentially fading stream. Each memory retrieval involves a new decoding and encoding to drive learning in the cortex through distillation/consolidation/retraining (this also helps prevent ontological crisis). The amygdala is a little cap on the edge of the hippocampus which connects to the various emotion subsystems and helps estimate the importance of current memories for prioritization in the HC.
A very strong retrieval of an episodic memory causes the inner experience of reliving the past (or imagining the future), but more typical weaker retrievals (those which load information into the cortex without overriding much of the existing context) are a crucial component in general higher cognition.
In short the computation that the HC performs is that of dynamic association between the current mental pattern/state loaded into short term memory across the cortex and some previous mental pattern/state. This is the very essence of creative insight.
Associative recall can be viewed as a type of pattern recognition with the attendant familiar tradeoffs between precision/recall or sensitivity/specificity. At the extreme of low recall high precision the network is very conservative and risk averse: it only returns high confidence associations, maximizing precision at the expense of recall (few associations found, many potentially useful matches are lost). At the other extreme is the over-confident crazy network which maximizes recall at the expense of precision (many associations are made, most of which are poor). This can also be viewed in terms of the exploitation vs exploration tradeoff.
This general analogy or framework - although oversimplified - also provides a useful perspective for understanding both schizotypy and hallucinogenic drugs. There is a large body of accumulated evidence in the form of use cases or trip reports, with a general consensus that hallucinogens can provide occasional flashes of creative insight at the expense of pushing one farther towards madness.
From a skeptical stance, using hallucinogenic drugs in an attempt to improve the mind is like doing surgery with butter-knives. Nonetheless, careful exploration of the sanity border can help one understand more on how the mind works from the inside.
Cannabis in particular is believed - by many of its users - to enhance creativity via occasional flashes of insight. Most of its main mental effects: time dilation, random associations, memory impairment, spatial navigation impairment, etc appear to involve the hippocampus. We could explain much of this as a general shift in the precision/recall tradeoff to make the hippocampus less selective. Mainly that makes the HC just work less effectively, but it also can occasionally lead to atypical creative insights, and appears to elevate some related low level measures such as schizotypy and divergent thinking[7]. The tradeoff is one must be willing to first sift through a pile of low value random associations.
Cultivate memetic heterogeneity and heterozygosity
Fluid intelligence is obviously important, but in many endeavors net creativity is even more important.
Of all the components underlying creativity, improving the efficiency of learning, the quality of knowledge learned, and the organizational efficiency of one's internal cortical maps are probably the most profitable dimensions of improvement: the low hanging fruits.
Our learning process is largely automatic and subconscious : we do not need to teach children how to perceive the world. But this just means it takes some extra work to analyze the underlying machinery and understand how to best utilize it.
Over long time scales humanity has learned a great deal on how to improve on natural innate learning: education is more or less learning-engineering. The first obvious lesson from education is the need for curriculum: acquiring concepts in stages of escalating complexity and order-dependency (which of course is already now increasingly a thing in machine learning).
In most competitive creative domains, formal education can only train you up to the starting gate. This of course is to be expected, for the creation of novel and useful ideas requires uncommon insights.
Memetic evolution is similar to genetic evolution in that novelty comes more from recombination than mutation. We can draw some additional practical lessons from this analogy: cultivate memetic heterogeneity and heterozygosity.
The first part - cultivate memetic heterogeneity - should be straightforward, but it is worth examining some examples. If you possess only the same baseline memetic population as your peers, then the chances of your mind evolving truly novel creative combinations are substantially diminished. You have no edge - your insights are likely to be common.
To illustrate this point, let us consider a few examples:
Geoffrey Hinton is one of the most successful researchers in machine learning - which itself is a diverse field. He first formally studied psychology, and then artificial intelligence. His various 200 research publications integrate ideas from statistics, neuroscience and physics. His work on boltzmann machines and variants in particular imports concepts from statistical physics whole cloth.
Before founding DeepMind (now one of the premier DL research groups in the world), Demis Hassabis studied the brain and hippocampus in particular at the Gatsby Computational Neuroscience Unit, and before that he worked for years in the video game industry after studying computer science.
Before the Annus Mirabilis, Einstein worked at the patent office for four years, during which time he was exposed to a large variety of ideas relating to the transmission of electric signals and electrical-mechanical synchronization of time, core concepts which show up in his later thought experiments.[8]
Creative people also tend to have a diverse social circle of creative friends to share and exchange ideas across fields.
Genetic heterozygosity is the quality of having two different alleles at a gene locus; summed over the organism this leads to a different but related concept of diversity.
Within developing fields of knowledge we often find key questions or subdomains for which there are multiple competing hypotheses or approaches. Good old fashioned AI vs Connectionism, Ray tracing vs Rasterization, and so on.
In these scenarios, it is almost always better to understand both viewpoints or knowledge clusters - at least to some degree. Each cluster is likely to have some unique ideas which are useful for understanding the greater truth or at the very least for later recombination.
This then is memetic heterozygosity. It invokes the Jain version of the blind men and the elephant.
Construct and maintain clean conceptual taxonomies
Formal education has developed various methods and rituals which have been found to be effective through a long process of experimentation. Some of these techniques are still quite useful for autodidacts.
When one sets out to learn, it is best to start with a clear goal. The goal of high school is just to provide a generalist background. In college one then chooses a major suitable for a particular goal cluster: do you want to become a computer programmer? a physicist? a biologist? etc. A significant amount of work then goes into structuring a learning curriculum most suitable for these goal types.
Once out of the educational system we all end up creating our own curriculums, whether intentionally or not. It can be helpful to think strategically as if planning a curriculum to suit one's longer term goals.
For example, about four years ago I decided to learn how the brain works and how AGI could be built in particular. When starting on this journey, I had a background mainly in computer graphics, simulation, and game related programming. I decided to focus about equally on mainstream AI, machine learning, computational neuroscience, and the AGI literature. I quickly discovered that my statistics background was a little weak, so I had to shore that up. Doing it all over again I may have started with a statistics book. Instead I started with AI: a modern approach (of course I mostly learn from the online research literature).
Learning works best when it is applied. Education exploits this principle and it is just as important for autodidactic learning. The best way to learn many math or programming concepts is learning by doing, where you create reasonable subtasks or subgoals for yourself along the way.
For general knowledge, application can take the form of writing about what you have learned. Academics are doing this all the time as they write papers and textbooks, but the same idea applies outside of academia.
In particular a good exercise is to imagine that you need to communicate all that you have learned about the domain. Imagine that you are writing a textbook or survey paper for example, and then you need to compress all that knowledge into a summary chapter or paper, and then all of that again down into an abstract. Then actually do write up a summary - at least in the form of a blog post (even if you don't show it to anybody).
The same ideas apply on some level to giving oral presentations or just discussing what you have learned informally - all of which are also features of the academic learning environment.
Early on, your first attempts to distill what you have learned into written form will be ... poor. But doing this process forces you to attempt to compress what you have learned, and thus it helps encourage the formation of well structured concept maps in the cortex.
A well structured conceptual map can be thought of as a memetic taxonomy. The point of a taxonomy is to organize all the invariances and 'is-a' relationships between objects so that higher level inferences and transformations can generalize well across categories.
Explicitly asking questions which probe the conceptual taxonomy can help force said structure to take form. For example in computer science/programming the question: "what is the greater generalization of this algorithm?" is a powerful tool.
In some domains, it may even be possible to semi-automate or at least guide the creative process using a structured method.
For example consider sci-fi/fantasy genre novels. Many of the great works have a general analogical structure based on real history ported over into a more exotic setting. The foundation series uses the model of the fall of the roman empire. Dune is like Lawrence of Arabia in space. Stranger in a Strange Land is like the Mormon version of Jesus the space alien, but from Mars instead of Kolob. A Song of Fire and Ice is partly a fantasy port of the war of the roses. And so on.
One could probably find some new ideas for novels just by creating and exploring a sufficiently large table of historical events and figures and comparing it to a map of the currently colonized space of ideas. Obviously having an idea for a novel is just the tiniest tip of the iceberg in the process, but a semi-formal method is interesting nonetheless for brainstorming and applies across domains (others have proposed similar techniques for generating startup ideas, for example).
Conclusion
We are born equipped with sophisticated learning machinery and yet lack innate knowledge on how to use it effectively - for this too we must learn.
The greatest constraint on creative ability is the quality of conceptual maps in the cortex. Understanding how these maps form doesn't automagically increase creativity, but it does help ground our intuitions and knowledge about learning, and could pave the way for future improved techniques.
In the meantime: cultivate memetic heterogeneity and heterozygosity, create a learning strategy, develop and test your conceptual taxonomy, continuously compress what you learn by writing and summarizing, and find ways to apply what you learn as you go.