18 results for "Max Tegmark"
Showing 1–18 · 0.10 seconds · RSS
-
Journal Article Full text
Improved Measures of Integrated Information.
Although there is growing interest in measuring integrated information in computational and cognitive systems, current methods for doing so in practice are computationally unfeasible. Existing and novel integration measures are investigated and classified by various desirable properties. A simple…
Also available at: PLOS
-
Journal Article Full text
Machine-learning media bias.
We present an automated method for measuring media bias. Inferring which newspaper published a given article, based only on the frequencies with which it uses different phrases, leads to a conditional probability distribution whose analysis lets us automatically map newspapers and phrases into a…
Also available at: PLOS
-
Journal Article Full text
How Do Transformers Model Physics? Investigating the Simple Harmonic Oscillator
How do transformers model physics? Do transformers model systems with interpretable analytical solutions or do they create an “alien physics” that is difficult for humans to decipher? We have taken a step towards demystifying this larger puzzle by investigating the simple harmonic oscillator (SHO)…
-
Journal Article Full text
Seeing Is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability
We introduce Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable. Inspired by brains, BIMT embeds neurons in a geometric space and augments the loss function with a cost proportional to the length of each neuron connection. This is inspired by…
-
Journal Article Full text
Precision Machine Learning
We explore unique considerations involved in fitting machine learning (ML) models to data with very high precision, as is often required for science applications. We empirically compare various function approximation methods and study how they scale with increasing parameters and data. We find that…
-
Journal Article Full text
Pareto-Optimal Clustering with the Primal Deterministic Information Bottleneck
At the heart of both lossy compression and clustering is a trade-off between the fidelity and size of the learned representation. Our goal is to map out and study the Pareto frontier that quantifies this trade-off. We focus on the optimization of the Deterministic Information Bottleneck (DIB)…
-
Journal Article Full text
AI Feynman: A physics-inspired method for symbolic regression
, and it discovers all of them, while previous publicly available software cracks only 71; for a more difficult physics-based test set, we improve the state-of-the-art success rate from 15 to 90%.
-
Journal Article Full text
Learnability for the Information Bottleneck
The Information Bottleneck (IB) method provides an insightful and principled approach for balancing compression and prediction for representation learning. The IB objective I ( X ; Z ) - β I ( Y ; Z ) employs a Lagrange multiplier β to tune this trade-off. However, in practice, not only is β chosen…
-
Journal Article
Kolmogorov-Arnold Networks Meet Science
A major challenge of AI plus science lies in its inherent incompatibility: Today’s AI is primarily based on connectionism, while science depends on symbolism. To bridge the two worlds, we propose a framework to seamlessly synergize Kolmogorov-Arnold networks (KANs) and science. The framework…
-
Journal Article
Toward a more accurate 3D atlas of C. elegans neurons
Abstract Background Determining cell identity in volumetric images of tagged neuronal nuclei is an ongoing challenge in contemporary neuroscience. Frequently, cell identity is determined by aligning and matching tags to an “atlas” of labeled neuronal positions and other identifying characteristics…
-
Journal Article Full text
The Geometry of Concepts: Sparse Autoencoder Feature Structure
Sparse autoencoders have recently produced dictionaries of high-dimensional vectors corresponding to the universe of concepts represented by large language models. We find that this concept universe has interesting structure at three levels: (1) The “atomic” small-scale structure contains…
-
Journal Article
Assessing whether artificial intelligence is an enabler or an inhibitor of sustainability at indicator level
Since the early phase of the artificial-intelligence (AI) era expectations towards AI are high, with experts believing that AI paves the way for managing and handling various global challenges. However, the significant enabling and inhibiting influence of AI for sustainable development needs to be…
-
Journal Article Full text
The role of artificial intelligence in achieving the Sustainable Development Goals
The emergence of artificial intelligence (AI) and its progressively wider impact on many sectors requires an assessment of its effect on the achievement of the Sustainable Development Goals. Using a consensus-based expert elicitation process, we find that AI can enable the accomplishment of 134…
Also available at: DOAJ
-
Journal Article Full text
Opening the AI Black Box: Distilling Machine-Learned Algorithms into Code
Can we turn AI black boxes into code? Although this mission sounds extremely challenging, we show that it is not entirely impossible by presenting a proof-of-concept method, MIPS, that can synthesize programs based on the automated mechanistic interpretability of neural networks trained to perform…
-
Journal Article
16p11.2 deletion is associated with hyperactivation of human iPSC-derived dopaminergic neuron networks and is rescued by RHOA inhibition in vitro
16p11.2 CNVs are associated with neurodevelopmental disorders. Here, the authors show that 16p11.2 deletion is associated with hyperactivation of human iPSC-derived dopaminergic neuron networks and is rescued by RHOA inhibition in vitro.