– you still need some prior to organize that infinite data and decide how to generalize from it
– the choice to minimize is an aesthetic choice, not a scientific one; evolution has clearly endowed many animals with significant priors (eg baby ibex climbing down a mountain).
RESEARCH
-
Innate Priors Shape AI Learning: Evolution Over Minimalism
By
–
-
Secret codeword for AGI existential risk research jobs
By
–
Is that like a secret codeword to get jobs in “AGI existential risk” research?
-
Deep Learning and AGI: Expectations vs Reality
By
–
Complaining deep learning is not AGI is like complaining a car doesn't fly.
-
Inductive Biases: Making Implicit Assumptions About Data Explicit
By
–
Inductive biases are always assumptions about the world generating the data. They may, however, be expressed very opaquely as network structure or even arbitrary hacks (easy and common but bad; you should make your assumptions explicit and then test/modify/refute them).
-
Data, Causality, and Action: Beyond Philosophical Definitions
By
–
But data can tell us what happens for every possible configuration of things that affect the barometer and the weather, including your actions. In this view, "causes" is a philosophical statement that is not required to guide your actions (or control a robot).
-
Strong innate priors in machine learning systems
By
–
that’s learning that the set of relevant cases is empty; it’s still a strong innate prior
-
Inductive bias guides learner function search in neural networks
By
–
Not exactly. The learner could well discover that none of the symmetries in the space hold. It's an inductive bias in the precise sense of the term: it causes the learner to search for some functions over others.
-
BIG-Bench Benchmarks Face Validity Scrutiny for AGI Predictions
By
–
Trouble in BIG-Bench paradise? – @ErnestSDavis looks at 48 of the benchmarks within and finds problems with most: https://
cs.nyu.edu/~davise/Benchm
arks/BigBenchDiscussion.html
… – Many project AGI timelines based on performance on these benchmarks. If the benchmarks aren’t valid, consequent timelines are problematic -
Algorithm discovers specific symmetries from defined possibility space
By
–
We tell them the space of possible symmetries (e.g., affine); the algorithm discovers which (e.g., translation, or some translations).
-
Learning Symmetries: Discovering Constraints in Phenomenon Modeling
By
–
The prior is that there's a space of symmetries the phenomenon being modeled may obey (e.g., affine), and the learning task is to discover which (e.g., only translations, or only some translations).