Concept of E-machine: How does a "dynamical" brain learn to process "symbolic" information? Part I
Victor Eliashberg
备注：
40 pages, 15 figures. The author is a consulting professor at the Stanford University, Department of Electrical Engineering and the president of Avel Electronics (consulting company)
The human brain has many remarkable information processing characteristics that deeply puzzle scientists and engineers. Among the most important and the most intriguing of these characteristics are the brain's broad universality as a learning system and its mysterious ability to dynamically change (reconfigure) its behavior depending on a combinatorial number of different contexts.
This paper discusses a class of hypothetically brain-like dynamically reconfigurable associative learning systems that shed light on the possible nature of these brain's properties. The systems are arranged on the general principle referred to as the concept of E-machine.
The paper addresses the following questions:
1. How can "dynamical" neural networks function as universal programmable "symbolic" machines?
2. What kind of a universal programmable symbolic machine can form arbitrarily complex software in the process of programming similar to the process of biological associative learning?
3. How can a universal learning machine dynamically reconfigure its software depending on a combinatorial number of possible contexts?
Emergent Language Symbolic Autoencoder (ELSA) with Weak Supervision to Model Hierarchical Brain Networks
Johns Hopkins University（约翰斯·霍普金斯大学）；Microsoft Health AI（微软健康人工智能）；Johns Hopkins School of Medicine（约翰斯·霍普金斯大学医学院）；Malone Center for Engineering in Healthcare, Johns Hopkins University（约翰斯·霍普金斯大学马龙医疗工程中心）
Industrial brain: a human-like autonomous neuro-symbolic cognitive decision-making system
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院，北京，中国）；School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China（人工智能学院，中国科学院大学，北京，中国）；School of Computer Science and Technology, East China Normal University, Shanghai, China（计算机科学与技术学院，华东师范大学，上海，中国）
Motivated by recent findings from cognitive neural science, we advocate the use of a dual-level model for concept representations: the embodied level consists of concept-oriented feature representations, and the symbolic level consists of concept graphs. Embodied concept representations are modality specific and exist in the form of feature vectors in a feature space. Symbolic concept representations, on the other hand, are amodal and language specific, and exist in the form of word / knowledge-graph embeddings in a concept / knowledge space. The human conceptual system comprises both embodied…
We propose neural-symbolic integration for abstract concept explanation and interactive learning. Neural-symbolic integration and explanation allow users and domain-experts to learn about the data-driven decision making process of large neural models. The models are queried using a symbolic logic language. Interaction with the user then confirms or rejects a revision of the neural model using logic-based constraints that can be distilled into the model architecture. The approach is illustrated using the Logic Tensor Network framework alongside Concept Activation Vectors and applied to a Convol…
Rate-Coding Bundle Memory: A Unified Model of Memory and Control for Symbolic Computation in the Brain
Max Planck Institute for Psycholinguistics（马克斯·普朗克心理语言学研究所）；Donders Institute for Brain, Cognition and Behaviour（唐德斯大脑、认知与行为研究所）；Radboud University（拉德堡德大学）
GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning
Technical University of Darmstadt（达姆施塔特技术大学）；Google Intrinsic（谷歌内在）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；Centre for Cognitive Science, TU Darmstadt（达姆施塔特技术大学认知科学中心）
University of Trento（特伦托大学）；University of Pisa（比萨大学）
Neuro-symbolic predictors learn a mapping from sub-symbolic inputs to higher-level concepts and then carry out (probabilistic) logical inference on this intermediate representation. This setup offers clear advantages in terms of consistency to symbolic prior knowledge, and is often believed to provide interpretability benefits in that - by virtue of complying with the knowledge - the learned concepts can be better understood by human stakeholders. However, it was recently shown that this setup is affected by reasoning shortcuts whereby predictions attain high accuracy by leveraging concepts wi…
Neural networks promote a distributed representation with no clear place for symbols. Despite this, we propose that symbols are manufactured simply by training a sparse random noise as a self-sustaining attractor in a feedback spiking neural network. This way, we can generate many of what we shall call prime attractors, and the networks that support them are like registers holding a symbolic value, and we call them registers. Like symbols, prime attractors are atomic and devoid of any internal structure. Moreover, the winner-take-all mechanism naturally implemented by spiking neurons enables r…
TU Darmstadt（达姆施塔特工业大学）；Hessian Center for AI (hessian.AI)（黑森人工智能中心）
Most explanation methods in deep learning map importance estimates for a model's prediction back to the original input space. These "visual" explanations are often insufficient, as the model's actual concept remains elusive. Moreover, without insights into the model's semantic concept, it is difficult -- if not impossible -- to intervene on the model's behavior via its explanations, called Explanatory Interactive Learning. Consequently, we propose to intervene on a Neuro-Symbolic scene representation, which allows one to revise the model on the semantic level, e.g. "never focus on the color to…
BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts
DISI, University of Trento（特伦托大学DISI学院）；DI, University of Pisa（比萨大学DI学院）；University of Edinburgh（爱丁堡大学）；CIMeC&DISI, University of Trento（特伦托大学CIMeC&DISI学院）
Alchemy is a new meta-learning environment rich enough to contain interesting abstractions, yet simple enough to make fine-grained analysis tractable. Further, Alchemy provides an optional symbolic interface that enables meta-RL research without a large compute budget. In this work, we take the first steps toward using Symbolic Alchemy to identify design choices that enable deep-RL agents to learn various types of abstraction. Then, using a variety of behavioral and introspective analyses we investigate how our trained agents use and represent abstract task variables, and find intriguing conne…
Center for Neural Science（神经科学中心）；New York University（纽约大学）；Department of Psychology and Center for Data Science（心理学系与数据科学中心）
Human conceptual knowledge supports the ability to generate novel yet highly structured concepts, and the form of this conceptual knowledge is of great interest to cognitive scientists. One tradition has emphasized structured knowledge, viewing concepts as embedded in intuitive theories or organized in complex symbolic knowledge structures. A second tradition has emphasized statistical knowledge, viewing conceptual knowledge as an emerging from the rich correlational structure captured by training neural networks and other statistical models. In this paper, we explore a synthesis of these two …
Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models
Department of Information Engineering and Computer Science, University of Trento, Italy（特伦托大学信息工程与计算机科学系）；CIMeC, University of Trento, Rovereto, Italy（特伦托大学罗韦雷托CIMeC）
The paper tackles four basic questions associated with human brain as a learning system. How can the brain learn to (1) mentally simulate different external memory aids, (2) perform, in principle, any mental computations using imaginary memory aids, (3) recall the real sensory and motor events and synthesize a combinatorial number of imaginary events, (4) dynamically change its mental set to match a combinatorial number of contexts? We propose a uniform answer to (1)-(4) based on the general postulate that the human neocortex processes symbolic information in a "nonclassical" way. Instead of m…
A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
DISI, University of Trento（特伦托大学DISI学院）；DI, University of Pisa（比萨大学DI学院）；Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会）；University of Padova（帕多瓦大学）；University of Edinburgh（爱丁堡大学）；CIMeC, University of Trento（特伦托大学CIMeC中心）
Closed-Form Interpretation of Neural Network Latent Spaces with Symbolic Gradients
University of Waterloo（多伦多大学）；Perimeter Institute for Theoretical Physics（理论物理研究所）；Homes Plus Magazine Inc.（Homes Plus 杂志公司）；University of Toronto（多伦多大学）
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；IIIS, Tsinghua University（清华大学交叉信息研究院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Deepmind（深度思考）；MIT BCS（麻省理工学院脑与认知科学系）；CBMM（脑、心智与机器中心）
We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; instead, our model learns by simply looking at images and reading paired questions and answers. Our model builds an object-based scene representation and translates sentences into executable, symbolic programs. To bridge the learning of two modules, we use a neuro-symbolic reasoning module that executes these programs on the latent scene representation. Analogical to human concept learning, the perception module learns…
UIUC（伊利诺伊大学厄巴纳-香槟分校）；U of Oregon（俄勒冈大学）；MIT-IBM Watson AI Lab & IBM Research（MIT-IBM沃森人工智能实验室与IBM研究院）；Picsart AI Research (PAIR)（Picsart AI研究（PAIR））
We study the problem of concept induction in visual reasoning, i.e., identifying concepts and their hierarchical relationships from question-answer pairs associated with images; and achieve an interpretable model via working on the induced symbolic concept space. To this end, we first design a new framework named object-centric compositional attention model (OCCAM) to perform the visual reasoning task with object-level visual features. Then, we come up with a method to induce concepts of objects and relations using clues from the attention patterns between objects' visual features and question…
People can learn rich, general-purpose conceptual representations from only raw perceptual inputs. Current machine learning approaches fall well short of these human standards, although different modeling traditions often have complementary strengths. Symbolic models can capture the compositional and causal knowledge that enables flexible generalization, but they struggle to learn from raw inputs, relying on strong abstractions and simplifying assumptions. Neural network models can learn directly from raw data, but they struggle to capture compositional and causal structure and typically must …
Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts
University of Trento（特伦托大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；Sapienza University of Rome（罗马大学）；University of Edinburgh（爱丁堡大学）；Huawei Labs（华为实验室）
Human-like Cognitive Generalization for Large Models via Brain-in-the-loop Supervision
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；State Key Lab of Brain-Machine Intelligence, Zhejiang University（浙江大学脑机智能全国重点实验室）
Explainable concept mappings of MRI: Revealing the mechanisms underlying deep learning-based brain disease classification
Medical University of Graz（格拉茨医科大学）；Monash University（莫纳什大学）；Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Technische Universität Berlin（柏林工业大学）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（BIFOLD——柏林学习与数据基础研究所）
Humans have the ability to rapidly understand rich combinatorial concepts from limited data. Here we investigate this ability in the context of auditory signals, which have been evolved in a cultural transmission experiment to study the emergence of combinatorial structure in language. We propose a neuro-symbolic generative model which combines the strengths of previous approaches to concept learning. Our model performs fast inference drawing on neural network methods, while still retaining the interpretability and generalization from limited data seen in structured generative approaches. This…
Taxonomic Networks: A Representation for Neuro-Symbolic Pairing
School of Interactive Computing（交互计算学院）；Georgia Institute of Technology（佐治亚理工学院）；College of Computing and Informatics（计算与信息学院）；Drexel University（德雷塞尔大学）
Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning
Beijing Institute for General Artificial Intelligence (BIGAI)（北京通用人工智能研究院（BIGAI））；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Yuanpei College, Peking University（北京大学元培学院）；University of California, Los Angeles (UCLA)（加利福尼亚大学洛杉矶分校）
A Brain-inspired Computational Model for Human-like Concept Learning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；International Research Center for AI Ethics and Governance, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所人工智能伦理与治理国际研究中心）；Center for Long-term Artificial Intelligence（长期人工智能研究中心）
University of Cambridge（剑桥大学）；Université Côte d’Azur（蔚蓝海岸大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；University of Siena（锡耶纳大学）；INRA（法国国家农业食品与环境研究院）；Université Paris-Saclay（巴黎萨克雷大学）；KU Leuven（鲁汶大学）
Siemens AG（西门子股份公司）；Technical University of Munich（慕尼黑工业大学）
Similarly to other connectionist models, Graph Neural Networks (GNNs) lack transparency in their decision-making. A number of sub-symbolic approaches have been developed to provide insights into the GNN decision making process. These are first important steps on the way to explainability, but the generated explanations are often hard to understand for users that are not AI experts. To overcome this problem, we introduce a conceptual approach combining sub-symbolic and symbolic methods for human-centric explanations, that incorporate domain knowledge and causality. We furthermore introduce the …
Center Leo Apostel for Interdisciplinary Studies（利奥·阿波斯特尔跨学科研究中心）；Brussels Free University（布鲁塞尔自由大学）
We identify the presence of typically quantum effects, namely 'superposition' and 'interference', in what happens when human concepts are combined, and provide a quantum model in complex Hilbert space that represents faithfully experimental data measuring the situation of combining concepts. Our model shows how 'interference of concepts' explains the effects of underextension and overextension when two concepts combine to the disjunction of these two concepts. This result supports our earlier hypothesis that human thought has a superposed two-layered structure, one layer consisting of 'classic…
University of Maryland, Baltimore County（马里兰大学巴尔的摩郡分校）；Laboratory for Physical Sciences（物理科学实验室）；Booz Allen Hamilton（博思艾伦汉密尔顿公司）
Holographic Reduced Representations (HRR) are a method for performing symbolic AI on top of real-valued vectors by associating each vector with an abstract concept, and providing mathematical operations to manipulate vectors as if they were classic symbolic objects. This method has seen little use outside of older symbolic AI work and cognitive science. Our goal is to revisit this approach to understand if it is viable for enabling a hybrid neural-symbolic approach to learning as a differentiable component of a deep learning architecture. HRRs today are not effective in a differentiable soluti…
