21 papers · ranked by Valyu relevance
Ana-Maria Olteţeanu, Mikkel Schöttner, Arpit Bahety
Re-representation is a critical ability to (i) understanding human creative problem solving, and (ii) modeling computational cognitive systems able to support or perform creative problem solving tasks on their own. This paper proposes a unified multi-level cognitive approach to investigating re-representation: the…
Jairo A. Navarrete, Pablo Dartnell, Paul Schrater
Category Theory, a branch of mathematics, has shown promise as a modeling framework for higher-level cognition. We introduce an algebraic model for analogy that uses the language of category theory to explore analogy-related cognitive phenomena. To illustrate the potential of this approach, we use this model to explore…
Thibaud Gruber, Klaus Zuberbühler, Fabrice Clément, Carel van Schaik
There is good evidence that some ape behaviors can be transmitted socially and that this can lead to group-specific traditions. However, many consider animal traditions, including those in great apes, to be fundamentally different from human cultures, largely because of lack of evidence for cumulative processes and…
Geraint A. Wiggins, Abdelrahman Sanjekdar
In this Hypothesis and Theory paper, we consider the problem of learning deeply structured knowledge representations in the absence of predefined ontologies, and in the context of long-term learning. In particular, we consider this process as a sequence of re-representation steps, of various kinds. The Information…
Zoran Josipovic
Some consider phenomenal consciousness to be the great achievement of the evolution of life on earth, but the real achievement is much more than mere phenomenality. The real achievement is that consciousness has woken up within us and has recognized itself, that within us humans, consciousness knows that it is…
Constantine Theocharis, Edwin Brady
Inductive families provide a convenient way of programming with dependent types. Yet, when it comes to compilation, their default linked-tree runtime representations, as well as the need to convert between different indexed views of the same data, can lead to unsatisfactory runtime performance. In this paper, we…
Sebastijan Veselic, Nour Mohsen, Lennart Luettgau, Elena Gutierrez + 5 more
Reasoning flexibly composes known elements to solve novel problems. Recent theories suggest the brain uses the axis of time to compose elements for reasoning. In this view, elements are packaged into fast neural sequences, with each sequence exploring the implications of a different composition. Using…
Shunsuke Onoo, Yoshihiro Nagano, Yukiyasu Kamitani
Sensory representation is typically understood through a hierarchical-causal framework where progressively abstract features are extracted sequentially. However, this causal view fails to explain misrepresentation, a phenomenon better handled by an informational view based on decodable content. This creates a tension…
Arnaud Plagnol
Underlying the theory of inferences, a primary task of logic is language analysis. Such a task can be understood as depending on a general theory of representation, taking as a starting point the idea that some entities (« representations ») can present some entites (« contents »). We outline a theory of representation…
Bowei Tian, Xuntao Lyu, Meng Liu, Hongyi Wang + 1 more
Representation Engineering (RepE) has emerged as a powerful paradigm for enhancing AI transparency by focusing on high-level representations rather than individual neurons or circuits. It has proven effective in improving interpretability and control, showing that representations can emerge, propagate, and shape final…
Ben Baker, Richard D. Lange, Andrew Richmond, Nikolaus Kriegeskorte + 3 more
Representations play a central role in the study of both biological and artificial intelligence, as well as philosophy of mind. Across neuroscience, computer science, and philosophy, a recurring theme is that representations not only carry information but should be ``useful'' for or ``usable'' by an agent in some…
Xin Chen, Sam Toyer, Cody Wild, Scott Emmons + 8 more
'Kuang-Huei Lee' 'Neel Alex' 'Steven H. Wang' 'Ping Luo' 'Stuart Russell' 'Pieter Abbeel' 'Rohin Shah'] | Xin Chen∗ | | Sam Toyer∗ | Cody Wild∗ | | | --- | --- | --- | --- | --- | | The University of Hong Kong | | UC Berkeley | UC Berkeley | | | cyn0531@connect.hku.hk | | sdt@berkeley.edu | codywild@berkeley.edu | | |…
Benjamin W. Roop, Benjamin Parrell, Adam C. Lammert
Uncovering cognitive representations is an elusive goal that is increasingly pursued using the reverse correlation method. Employing reverse correlation often entails collecting thousands of stimulus-response pairs from human subjects, a burdensome task that limits the feasibility of many such studies. This…
Authors not listed
Machine learning is increasingly used to predict reaction properties such as barrier heights, reaction energies, rates, or yields, as well as the underlying molecular geometries, including transition state structures. While such predictions have the potential to provide mechanistic insight for high-impact applications…
Authors not listed
Many successful machine learning models for molecular property prediction rely on Lewis structure representations, commonly encoded as SMILES strings. However, a key limitation arises with molecules exhibiting resonance, where multiple valid Lewis structures represent the same species. This causes inconsistent…
Eamon Duede
This paper aims to clarify the representational status of Deep Learning Models (DLMs). While commonly referred to as 'representations', what this entails is ambiguous due to a conflation of functional and relational conceptions of representation. This paper argues that while DLMs represent their targets in a relational…
Rishabh Raj, Dar Dahlen, Kyle Duyck, C. Ron Yu
The brain has a remarkable ability to recognize objects from noisy or corrupted sensory inputs. How this cognitive robustness is achieved computationally remains unknown. We present a coding paradigm, which encodes structural dependence among features of the input and transforms various forms of the same input into the…
Anthony Onwuli, Keith T. Butler, Aron Walsh
High-dimensional representations of the elements have become common within the field of materials informatics to build useful, structure-agnostic models for the chemistry of materials. However, the characteristics of elements change when they adopt a given oxidation state, with distinct structural preferences and…
Zitong Lu, Yixuan Ku
Facial repetition suppression, a well-studied phenomenon characterized by decreased neural responses to repeated faces in visual cortices, remains a subject of ongoing debate regarding its underlying neural mechanisms. Recent advancements have seen deep convolutional neural networks (DCNNs) achieve human-level…
Philippe G. Schyns, Robin A.A. Ince
A fundamental challenge in neuroscience is to understand how the brain processes information. Neuroscientists have approached this question partly by measuring brain activity in space, time and at different levels of granularity. However, our aim is not to discover brain activity per se, but to understand the…
Authors not listed
Quantum state tomography has been widely used to reconstruct the quantum state of a system from a set of informationally-complete measurements. Obtaining enough information about, e.g., the wavefunction of a molecule allows its complete characterization. On the other hand, deep learning models for molecular property…