4 min and 40 sec to read, 1167 words
Another concept that is closely related to prediction is that of surprise. If we predict X and what instead happens is sufficiently different from X we experience a specific feeling of surprise — but the outcome needs to not just be different in some small degree, but in a very specific way. The way an outcome needs to be different from the prediction suggests that around every predicted outcome there is a zone of expected outcomes, and at some point this reverts into a zone of surprise.
Surprise has been the subject of research of different kinds. One of the more intriguing papers in this field is “Surprise: a unified theory and experimental predictions.” By Alireza, Johanni and Wulfram. 1 See Alireza, Modirshanechi., Johanni, Brea., Wulfram, Gerstner. (2021). Surprise: a unified theory and experimental predictions. bioRxiv, Available from: 10.1101/2021.11.01.466796 In this paper the authors detail 16 different kinds of surprise, delving into the nature of surprise at an admirable depth.
They organize these 16 variations into 4 categories:
We classify these surprise measures into four main categories: (i) change-point detection surprise, (ii) information gain surprise, (iii) prediction surprise, and (iv) confidence-correction surprise.
They also explore what different kinds of cognitive strategies – such as surprise seeking – may be most beneficial in certain situations, which is a fascinating question.
In their analysis of surprise measures, the authors identify several distinct categories, each associated with different cognitive strategies. Prediction surprise, exemplified by what they call Shannon surprise, focuses on how unexpected an observation is and aligns with the strategy of making accurate predictions about future events. Change-point detection surprise, such as the Bayes Factor surprise, is geared towards identifying shifts in the environment and supports adaptive learning in volatile conditions. Confidence correction surprise incorporates the certainty of one’s beliefs, modulating surprise based on confidence levels. Information gain surprise, like Bayesian surprise, quantifies belief updates and promotes efficient exploration and model-building of the environment.
The authors argue that these categories reflect different cognitive functions and strategies: prediction surprise matches our intuitive understanding of surprise, change-point detection surprise is crucial for adapting learning rates, and information gain surprise is optimal for exploration.
We do not need to go this far, however, to further explore the relationship between prediction and surprise – we can establish some rough sketches before we start looking deeper.
Surprise is the result of a difference between the predicted outcome O(x) and the observed outcome O(y) – and from an evolutionary perspective the ability to be surprised must have been beneficial and selected for not just because the feeling of surprise itself is pleasant or important, but because of the actions we take following being surprised – surprise enables us to adapt to changes in the environment and to prioritize the changes that deviate most from the range of predicted outcomes (and hence the ones that carry most risk).2 This is explored in Rainer, Reisenzein., Gernot, Horstmann., Achim, Schützwohl. (2019). The Cognitive-Evolutionary Model of Surprise: A Review of the Evidence.. Topics in Cognitive Science, Available from: 10.1111/TOPS.12292 and in Ned, Kock., Ruth, Chatelain-Jardon., Jesus, Carmona. (2010). Surprise and Human Evolution: How a Snake Screen Enhanced Knowledge Transfer Through a Web Interface. Available from: 10.1007/978-1-4419-6139-6_5 – where the argument is made that surprise is followed be increased cognitive focus and function.
That means that predictions come with a surprise tolerance that has also evolved — there is a corona of expectation around a prediction that protect us from being surprised all the time by any minor deviation. This corona corresponds to a larger set of outcomes O(x(1))…O(x(n)) that are perceived as variations on O(x) – and then there is a the surprise zone where we have deviated enough from the expected outcome to trigger surprise as a survival reaction.
Where is that boundary and is it different for different predictions? It probably is – and that has to do both with the importance and salience of the prediction to us, and the amount of knowledge we believe we have about the predicted outcome.
And what is the opposite of surprise, the sense of confirmation that we get when we sense that we predicted something accurately?
In a game of prediction, the role of surprise is also interesting. By trying to determine the opponents zone of surprise, I can also understand better where different plays will be less expected, and where my opponent will have to spend significant energy to adapt.
This means that by studying predictions, I can craft surprise.
While this is not surprising (!), it is an interesting observation for anyone interested in military affairs — and also features as a major component in military strategy, where the creation of both tactical and strategy surprise is a key skill that strategists study and try to develop. The best way of doing that is to carefully study the predictions of both our own side and that of the opponent — leading to a search in the space of predictions for the surprise boundaries.
*
There is also, as shown above, some direct implications for how we craft our predictions here. A good prediction, then, is one that allows for us to be surprised in the most productive way we can imagine! This, in turn, means that we should explore and value predictions based on the potential surprise that they entail – and perhaps even define surprise boundaries beforehand as we think closely about how we want our future selves to react to the outcomes of our predictions.
This is especially important, since surprise is culturally complicated and normatively difficult: we do not like being surprised, and so we explain way the results of a bad prediction to seem as we were aware the whole time that the actual outcome was reasonably easy to expect. 3 Why is this? Why do we find being surprised shameful? If being surprised is an evolutionary advantage we should instead celebrate it as a feeling, but there are probably several mechanisms at play here: one is that children are surprised by many things, and we associate that with a not yet formed model of the world: playing peekaboo with a small child is a reminder that they can be surprised again and again by us hiding behind our own hands. This in turn suggests that being surprised means that your model of the world is weak. But nothing could be more wrong — if you repeatedly get surprised at the same thing, for sure, but not if you seek new surprises. Another possible explanation is that we have also evolved to project confidence because that is a need for tribal cohesion . This means that our confidence and surprise are in conflict, and so when we are safe we do not seek surprise as much as when we are in an ambiguous state? Perhaps.
We need to actively ensure to safeguard our surprise instead and learn to relish it. Being surprised several times a day is a good thing.
Footnotes and references
- 1See Alireza, Modirshanechi., Johanni, Brea., Wulfram, Gerstner. (2021). Surprise: a unified theory and experimental predictions. bioRxiv, Available from: 10.1101/2021.11.01.466796
- 2This is explored in Rainer, Reisenzein., Gernot, Horstmann., Achim, Schützwohl. (2019). The Cognitive-Evolutionary Model of Surprise: A Review of the Evidence.. Topics in Cognitive Science, Available from: 10.1111/TOPS.12292 and in Ned, Kock., Ruth, Chatelain-Jardon., Jesus, Carmona. (2010). Surprise and Human Evolution: How a Snake Screen Enhanced Knowledge Transfer Through a Web Interface. Available from: 10.1007/978-1-4419-6139-6_5 – where the argument is made that surprise is followed be increased cognitive focus and function.
- 3Why is this? Why do we find being surprised shameful? If being surprised is an evolutionary advantage we should instead celebrate it as a feeling, but there are probably several mechanisms at play here: one is that children are surprised by many things, and we associate that with a not yet formed model of the world: playing peekaboo with a small child is a reminder that they can be surprised again and again by us hiding behind our own hands. This in turn suggests that being surprised means that your model of the world is weak. But nothing could be more wrong — if you repeatedly get surprised at the same thing, for sure, but not if you seek new surprises. Another possible explanation is that we have also evolved to project confidence because that is a need for tribal cohesion . This means that our confidence and surprise are in conflict, and so when we are safe we do not seek surprise as much as when we are in an ambiguous state? Perhaps.
Leave a Reply to Nicklas LundbladCancel reply