Megan A. K. Peters

Patrick Butlin, Robert Long, Eric Elmoznino et al.

Whether current or near-term AI systems could be conscious is a topic of scientific interest and increasing public concern. This report argues for, and exemplifies, a rigorous and empirically grounded approach to AI consciousness: assessing existing AI systems in detail, in light of our best-supported neuroscientific theories of consciousness. We survey several prominent scientific theories of consciousness, including recurrent processing theory, global workspace theory, higher-order theories, predictive processing, and attention schema theory. From these theories we derive "indicator properties" of consciousness, elucidated in computational terms that allow us to assess AI systems for these properties. We use these indicator properties to assess several recent AI systems, and we discuss how future systems might implement them. Our analysis suggests that no current AI systems are conscious, but also suggests that there are no obvious technical barriers to building AI systems which satisfy these indicators.

Seyedmehdi Orouji, Vincent Taschereau-Dumouchel, Aurelio Cortese et al.

In human neuroscience, machine learning can help reveal lower-dimensional neural representations relevant to subjects' behavior. However, state-of-the-art models typically require large datasets to train, so are prone to overfitting on human neuroimaging data that often possess few samples but many input dimensions. Here, we capitalized on the fact that the features we seek in human neuroscience are precisely those relevant to subjects' behavior. We thus developed a Task-Relevant Autoencoder via Classifier Enhancement (TRACE), and tested its ability to extract behaviorally-relevant, separable representations compared to a standard autoencoder, a variational autoencoder, and principal component analysis for two severely truncated machine learning datasets. We then evaluated all models on fMRI data from 59 subjects who observed animals and objects. TRACE outperformed all models nearly unilaterally, showing up to 12% increased classification accuracy and up to 56% improvement in discovering "cleaner", task-relevant representations. These results showcase TRACE's potential for a wide variety of data related to human behavior.

Mark Steyvers, Megan A. K. Peters

Metacognition--the capacity to monitor and evaluate one's own knowledge and performance--is foundational to human decision-making, learning, and communication. As large language models (LLMs) become increasingly embedded in both high-stakes and widespread low-stakes contexts, it is important to assess whether, how, and to what extent they exhibit metacognitive abilities. Here, we provide an overview of current knowledge of LLMs' metacognitive capacities, how they might be studied, and how they relate to our knowledge of metacognition in humans. We show that while humans and LLMs can sometimes appear quite aligned in their metacognitive capacities and behaviors, it is clear many differences remain; attending to these differences is important for enhancing human-AI collaboration. Finally, we discuss how endowing future LLMs with more sensitive and more calibrated metacognition may also help them develop new capacities such as more efficient learning, self-direction, and curiosity.

Hojjat Azimi Asrari, Megan A. K. Peters

Studies often aim to reveal ``first-order" representations (FORs), which encode aspects of an observer's environment, such as contents or structure. A less-common target is ``higher-order" representations (HORs), which are ``about" FORs -- e.g., their strength or uncertainty -- and which may contribute to learning. HORs about uncertainty are unlikely to be direct ``read-outs" of FOR characteristics, instead reflecting noisy estimation processes incorporating prior expectations about uncertainty, but how the brain represents such expected uncertainty distributions remains largely unexplored. Here, we study ``noise expectation" HORs using neural data from a task which may require the brain to learn about its own noise: decoded neurofeedback, wherein human subjects learn to volitionally produce target neural patterns. We develop and apply a Noise Estimation through Reinforcement-based Diffusion (NERD) model to characterize how brains may undertake this process, and show that NERD offers high explanatory power for human behavior.

Federica Zoe Ricci, Erik B. Sudderth, Jaylen Lee et al.

We consider the problem of analyzing multivariate time series collected on multiple subjects, with the goal of identifying groups of subjects exhibiting similar trends in their recorded measurements over time as well as time-varying groups of associated measurements. To this end, we propose a Bayesian model for temporal biclustering featuring nested partitions, where a time-invariant partition of subjects induces a time-varying partition of measurements. Our approach allows for data-driven determination of the number of subject and measurement clusters as well as estimation of the number and location of changepoints in measurement partitions. To efficiently perform model fitting and posterior estimation with Markov Chain Monte Carlo, we derive a blocked update of measurements' cluster-assignment sequences. We illustrate the performance of our model in two applications to functional magnetic resonance imaging data and to an electroencephalogram dataset. The results indicate that the proposed model can combine information from potentially many subjects to discover a set of interpretable, dynamic patterns. Experiments on simulated data compare the estimation performance of the proposed model against ground-truth values and other statistical methods, showing that it performs well at identifying ground-truth subject and measurement clusters even when no subject or time dependence is present.