Beyond Attention: Toward Machines with Intrinsic Higher Mental States

• URL: http://arxiv.org/abs/2505.06257v1
• Date: Fri, 02 May 2025 14:31:10 GMT
• Title: Beyond Attention: Toward Machines with Intrinsic Higher Mental States
• Abstract summary: This work shows how models (e.g., Transformers) can emulate high-level perceptual processing and awake thought (imagination) states.<n>Results span reinforcement learning (e.g., CarRacing in a high-dimensional visual setup), computer vision, and natural language question answering.
• Score: 1.2147145617662436
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Attending to what is relevant is fundamental to both the mammalian brain and modern machine learning models such as Transformers. Yet, determining relevance remains a core challenge, traditionally offloaded to learning algorithms like backpropagation. Inspired by recent cellular neurobiological evidence linking neocortical pyramidal cells to distinct mental states, this work shows how models (e.g., Transformers) can emulate high-level perceptual processing and awake thought (imagination) states to pre-select relevant information before applying attention. Triadic neuronal-level modulation loops among questions ($Q$), clues (keys, $K$), and hypotheses (values, $V$) enable diverse, deep, parallel reasoning chains at the representation level and allow a rapid shift from initial biases to refined understanding. This leads to orders-of-magnitude faster learning with significantly reduced computational demand (e.g., fewer heads, layers, and tokens), at an approximate cost of $\mathcal{O}(N)$, where $N$ is the number of input tokens. Results span reinforcement learning (e.g., CarRacing in a high-dimensional visual setup), computer vision, and natural language question answering.

Related papers

• Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding [19.258438045449846]
  We introduce a meta-optimized approach for semantic visual decoding from fMRI.<n>Our approach is explicitly optimized for in-context learning of the new subject's encoding model.<n>We demonstrate strong cross-subject and cross-scanner generalization across diverse visual backbones without retraining or fine-tuning.
  arXiv  Detail & Related papers  (2026-04-09T17:59:32Z)
• Scalable Machines with Intrinsic Higher Mental-State Dynamics [1.5584040836686046]
  This work introduces a mathematically grounded formulation showing how models (e.g., Transformers) can implement computational principles underlying awake imaginative thought.<n>Experiments on ImageNet-1K, benchmarked against a standard Vision Transformer (ViT), demonstrate significantly faster learning with reduced computational demand.
  arXiv  Detail & Related papers  (2026-03-13T16:16:50Z)
• Language Model Circuits Are Sparse in the Neuron Basis [50.460651620833055]
  We show that textbfMLP neurons are as sparse a feature basis as SAEs.<n>This work advances automated interpretability of language models without additional training costs.
  arXiv  Detail & Related papers  (2026-01-30T05:41:19Z)
• A Convolutional Framework for Mapping Imagined Auditory MEG into Listened Brain Responses [0.0]
  We present a Magnetoencephalography (MEG) dataset collected from trained musicians as they imagined and listened to musical and poetic stimuli.<n>We show that both imagined and perceived brain responses contain consistent, condition-specific information.
  arXiv  Detail & Related papers  (2025-12-03T05:23:10Z)
• Unsupervised representation learning with Hebbian synaptic and structural plasticity in brain-like feedforward neural networks [0.0]
  We introduce and evaluate a brain-like neural network model capable of unsupervised representation learning.<n>The model was tested on a diverse set of popular machine learning benchmarks.
  arXiv  Detail & Related papers  (2024-06-07T08:32:30Z)
• Brain-inspired Computational Intelligence via Predictive Coding [73.42407863671565]
  Predictive coding (PC) has shown promising properties that make it potentially valuable for the machine learning community.<n>PC-like algorithms are starting to be present in multiple sub-fields of machine learning and AI at large.
  arXiv  Detail & Related papers  (2023-08-15T16:37:16Z)
• Redundancy and Concept Analysis for Code-trained Language Models [5.726842555987591]
  Code-trained language models have proven to be highly effective for various code intelligence tasks. They can be challenging to train and deploy for many software engineering applications due to computational bottlenecks and memory constraints. We perform the first neuron-level analysis for source code models to identify textitimportant neurons within latent representations.
  arXiv  Detail & Related papers  (2023-05-01T15:22:41Z)
• BrainBERT: Self-supervised representation learning for intracranial recordings [18.52962864519609]
  We create a reusable Transformer, BrainBERT, for intracranial recordings bringing modern representation learning approaches to neuroscience. Much like in NLP and speech recognition, this Transformer enables classifying complex concepts, with higher accuracy and with much less data. In the future, far more concepts will be decodable from neural recordings by using representation learning, potentially unlocking the brain like language models unlocked language.
  arXiv  Detail & Related papers  (2023-02-28T07:40:37Z)
• Are Deep Neural Networks SMARTer than Second Graders? [85.60342335636341]
  We evaluate the abstraction, deduction, and generalization abilities of neural networks in solving visuo-linguistic puzzles designed for children in the 6--8 age group. Our dataset consists of 101 unique puzzles; each puzzle comprises a picture question, and their solution needs a mix of several elementary skills, including arithmetic, algebra, and spatial reasoning. Experiments reveal that while powerful deep models offer reasonable performances on puzzles in a supervised setting, they are not better than random accuracy when analyzed for generalization.
  arXiv  Detail & Related papers  (2022-12-20T04:33:32Z)
• Sequence learning in a spiking neuronal network with memristive synapses [0.0]
  A core concept that lies at the heart of brain computation is sequence learning and prediction. Neuromorphic hardware emulates the way the brain processes information and maps neurons and synapses directly into a physical substrate. We study the feasibility of using ReRAM devices as a replacement of the biological synapses in the sequence learning model.
  arXiv  Detail & Related papers  (2022-11-29T21:07:23Z)
• Transformers Learn Shortcuts to Automata [52.015990420075944]
  We find that a low-depth Transformer can represent the computations of any finite-state automaton. We show that a Transformer with $O(log T)$ layers can exactly replicate the computation of an automaton on an input sequence of length $T$. We further investigate the brittleness of these solutions and propose potential mitigations.
  arXiv  Detail & Related papers  (2022-10-19T17:45:48Z)
• Abductive Knowledge Induction From Raw Data [12.868722327487752]
  We present Abductive Meta-Interpretive Learning ($Meta_Abd$) that unites abduction and induction to learn neural networks and induce logic theories jointly from raw data. Experimental results demonstrate that $Meta_Abd$ not only outperforms the compared systems in predictive accuracy and data efficiency.
  arXiv  Detail & Related papers  (2020-10-07T16:33:28Z)
• Towards Understanding Hierarchical Learning: Benefits of Neural Representations [160.33479656108926]
  In this work, we demonstrate that intermediate neural representations add more flexibility to neural networks. We show that neural representation can achieve improved sample complexities compared with the raw input. Our results characterize when neural representations are beneficial, and may provide a new perspective on why depth is important in deep learning.
  arXiv  Detail & Related papers  (2020-06-24T02:44:54Z)
• Towards a Neural Model for Serial Order in Frontal Cortex: a Brain Theory from Memory Development to Higher-Level Cognition [53.816853325427424]
  We propose that the immature prefrontal cortex (PFC) use its primary functionality of detecting hierarchical patterns in temporal signals. Our hypothesis is that the PFC detects the hierarchical structure in temporal sequences in the form of ordinal patterns and use them to index information hierarchically in different parts of the brain. By doing so, it gives the tools to the language-ready brain for manipulating abstract knowledge and planning temporally ordered information.
  arXiv  Detail & Related papers  (2020-05-22T14:29:51Z)
• PuzzLing Machines: A Challenge on Learning From Small Data [64.513459448362]
  We introduce a challenge on learning from small data, PuzzLing Machines, which consists of Rosetta Stone puzzles from Linguistic Olympiads for high school students. Our challenge contains around 100 puzzles covering a wide range of linguistic phenomena from 81 languages. We show that both simple statistical algorithms and state-of-the-art deep neural models perform inadequately on this challenge, as expected.
  arXiv  Detail & Related papers  (2020-04-27T20:34:26Z)
• Machine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning [95.18337034090648]
  We propose a dataset, Machine Number Sense (MNS), consisting of visual arithmetic problems automatically generated using a grammar model--And-Or Graph (AOG) These visual arithmetic problems are in the form of geometric figures. We benchmark the MNS dataset using four predominant neural network models as baselines in this visual reasoning task.
  arXiv  Detail & Related papers  (2020-04-25T17:14:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.