Gene

Marketing

Deep neural networks

Transfer of learning

Robustness (evolution)

Benchmarking

Economics

Biochemistry

Computer science

Business

Management

Transferability

Data science

Artificial intelligence

Logit

Chemistry

Deep learning

Artificial neural network

Perspective (graphical)

Machine learning

Nature Machine Intelligence

Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today's machine intelligence. Numerous success stories have rapidly spread all over science, industry and society, but its limitations have only recently come into focus. In this perspective we seek to distil how many of deep learning's problem can be seen as different symptoms of the same underlying problem: shortcut learning. Shortcuts are decision rules that perform well on standard benchmarks but fail to transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in Comparative Psychology, Education and Linguistics, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial alike. Based on these observations, we develop a set of recommendations for model interpretation and benchmarking, highlighting recent advances in machine learning to improve robustness and transferability from the lab to real-world applications.

Shortcut learning in deep neural networks