REVIEW 5 cited by
Shortcut Learning in Deep Neural Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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 distill how many of deep learning's problems 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.
Forward citations
Cited by 5 Pith papers
-
The Equilibrium Is the Initialization: Lazy Identity Collapse in Physics-Structured Deep Equilibrium Reasoning
In a port-Hamiltonian DEQ with learned initialization, the equilibrium equals the start to numerical precision and contributes +0.00 pp accuracy in 18 of 19 runs; a four-test diagnostic exposes the no-op.
-
Discriminative Axis, Not Data Volume: What a Contrastive Corpus Teaches an Audio Embedding
A contrastive audio embedding learns an attribute only when in-batch negatives cannot be separated without it, so corpus structure, not size or caption vocabulary, controls what is encoded.
-
Structure and Destructure: Dual Forces in the Making of Knowledge Engines
Language modeling objectives induce recoverable structure in both graph and text models, and periodically resetting embeddings improves their plasticity; together these two forces unify structured and unstructured kno...
-
Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language
Research on AI 'scheming' repeats the methodological errors of 1970s ape language studies, relying on anecdote and mentalistic interpretation instead of controlled, theory-driven tests.
-
CLARK: Closed-loop Learning for Adaptive Reasoning over Knowledge Graphs
CLARK improves medical classification by iteratively enriching a knowledge graph with mined logical rules calibrated through LP^MLN probabilistic reasoning.
Discussion (0). Sign in to comment.