Trends in Cognitive Sciences
OpinionDeep Neural Networks as Scientific Models
Section snippets
The Contested Value of Deep Neural Networks in Cognitive Science
In recent years, neurally inspired 1, 2 artificial deep neural networks (DNNs; see Glossary) have revolutionised first computer vision [3] and subsequently other domains such as natural language processing [4], control and planning (such as playing games, e.g., Atari and Go 5, 6), and navigational tasks (such as finding the shortest path on a subway map [7]).
DNNs are computational models consisting of many simple processing units (akin to neurons) that work in parallel and are arranged in
The Nature of Good Scientific Models
To evaluate whether DNNs are good scientific models, we need to agree on what makes a good model in the first place. Can we formulate a list of properties good models fulfil and check DNNs against these properties? Or, can we select a particular model that we believe to be an excellent scientific model as a standard and compare DNNs against it? Reflecting on the use of models in a broader scientific context, we argue that the case is not as simple as that.
The Predictive Power of DNNs
In technology and engineering the primary goal is to create artefacts that do things (i.e., correctly predict a particular outcome), while explanation often takes second place [33]. Are DNNs useful in cognitive science in this way? While DNN critics concede the predictive power of DNNs, they often dismiss it as less valuable for science than explanation. Here, we affirm the value of prediction on two grounds.
A pragmatic reason is that due to its predictive power a DNN could be used akin to a
The Explanatory Power of DNNs
How can a model do explanatory work in cognitive science (Box 2)? The blueprint notion many researchers have in mind is so-called mathematical–theoretical modelling 43, 44. There, a few relevant variables for describing a phenomenon are identified, it is hypothesised how they interact, and the variables and their interaction are modelled mathematically. Each variable is a priori linked to a part of the phenomenon modelled in the world, such that changes in the model variable are directly
The Exploratory Power of DNNs
An idealised view of natural science is that it proceeds by deriving hypotheses from a theory and testing them in experiments. But what to do if a fully-fledged and convincing theory is missing? Then we need to explore 64, 65 to create starting points for new theories, rather than predict or explain. This means a shift of perspective from models as tools for predictions, or akin to theories for explanation, to exploration [21].
Observing the scientific practise indicates that exploration is an
Concluding Remarks and Future Directions
Taking a bird’s-eye view from the stance of philosophy of science, we took a fresh look on what is at stake in the debate on DNNs as models for behaviour and neural activity. We emphasise four take-home messages for future research (Figure 2). First, given the current level of theory development and the need to trade-off model desiderata, we should embrace DNNs as one of many diverse kinds of useful models. Second, through their predictive power DNNs have rich potential as tools for scientific
Acknowledgments
We thank Aude Oliva and Philippe Schyns for thoughtful comments and feedback. This work was supported by Deutsche Forschungsgemeinschaft (DFG) grants awarded to R.M.C. (CI241/1-1, CI241/3-1) and D.K. (KA4683/2-1).
Glossary
- Analogy
- a similarity between relations in two different domains.
- Box-and-arrow model
- a model of information processing in which boxes represent components of an information processing system, and arrows represent information flow between those components.
- Deep neural network
- a computer algorithm inspired by biological neural networks, consisting of units akin to neurons and defined in function by the connection between the units (Figure 1A). Units are often not connected to all other units but
References (93)
Learning multiple layers of representation
Trends Cogn. Sci.
(2007)Seeing it all: convolutional network layers map the function of the human visual system
Neuroimage
(2017)Trade-offs in model-building: a more target-oriented approach
Stud. Hist. Philos. Sci. Part A
(2011)Modelling and representing: an artefactual approach to model-based representation
Stud. Hist. Philos. Sci. A
(2011)The morals of model-making
Stud. Hist. Philos. Sci. A
(2014)Neuroscience-inspired artificial intelligence
Neuron
(2017)Cognitive computational neuroscience: a new conference for an emerging discipline
Trends Cogn. Sci.
(2018)Parallel Distributed Processing
(1987)- et al.
A logical calculus of the ideas immanent in nervous activity
Bull. Math. Biophys.
(1943) Imagenet classification with deep convolutional neural networks
Adv. Neural Inform. Process. Syst.
(2012)