Recent advances in programming languages study and design have established a standard way of grounding computational systems representation in category theory. These formal results led to a better understanding of issues of control and side-effects in functional and imperative languages. This framework can be successfully applied to the investigation of the performance of Artificial Intelligence (AI) inference and cognitive systems. In this paper, we delineate a categorical formalisation of memory as a control structure driving performance in inference systems. Abstracting away control mechanisms from three widely used representations of memory in cognitive systems (scripts, production rules and clusters) we explain how categorical triples capture the interaction between learning and problem-solving.
Mississippi State University（密西西比州立大学）；Queens College/CUNY（皇后学院/纽约市立大学）
A limited-memory influence diagram (LIMID) generalizes a traditional influence diagram by relaxing the assumptions of regularity and no-forgetting, allowing a wider range of decision problems to be modeled. Algorithms for solving traditional influence diagrams are not easily generalized to solve LIMIDs, however, and only recently have exact algorithms for solving LIMIDs been developed. In this paper, we introduce an exact algorithm for solving LIMIDs that is based on branch-and-bound search. Our approach is related to the approach of solving an influence diagram by converting it to an equivale…
Mamba with Hierarchical Memory: Solving Representation Bottleneck in Long Sequence Modeling
The Hong Kong University of Science and Technology（香港科技大学）；University of Oxford（牛津大学）；The Chinese University of Hong Kong（香港中文大学）；City University of Hong Kong（香港城市大学）；Hainan Bielefeld University of Applied Sciences（海南比勒费尔德应用科学大学）；BrainGalaxy
We present a memory-bounded optimization approach for solving infinite-horizon decentralized POMDPs. Policies for each agent are represented by stochastic finite state controllers. We formulate the problem of optimizing these policies as a nonlinear program, leveraging powerful existing nonlinear optimization techniques for solving the problem. While existing solvers only guarantee locally optimal solutions, we show that our formulation produces higher quality controllers than the state-of-the-art approach. We also incorporate a shared source of randomness in the form of a correlation device t…
We present a new algorithm for exactly solving decision making problems represented as influence diagrams. We do not require the usual assumptions of no forgetting and regularity; this allows us to solve problems with simultaneous decisions and limited information. The algorithm is empirically shown to outperform a state-of-the-art algorithm on randomly generated problems of up to 150 variables and $10^{64}$ solutions. We show that the problem is NP-hard even if the underlying graph structure of the problem has small treewidth and the variables take on a bounded number of states, but that a fu…
Universidade de Évora（埃武拉大学）；CENTRIA FCT/UNL（新里斯本大学科学技术中心）；University of Paris 1-Sorbonne（巴黎第一大学-索邦大学）；JFLI, CNRS / UPMC / University of Tokyo（日本法语实验室，法国国家科学研究中心/巴黎第六大学/东京大学）
We explore the use of the Cell Broadband Engine (Cell/BE for short) for combinatorial optimization applications: we present a parallel version of a constraint-based local search algorithm that has been implemented on a multiprocessor BladeCenter machine with twin Cell/BE processors (total of 16 SPUs per blade). This algorithm was chosen because it fits very well the Cell/BE architecture and requires neither shared memory nor communication between processors, while retaining a compact memory footprint. We study the performance on several large optimization benchmarks and show that this achieves…
An integral function of fully autonomous robots and humans is the ability to focus attention on a few relevant percepts to reach a certain goal while disregarding irrelevant percepts. Humans and animals rely on the interactions between the Pre-Frontal Cortex (PFC) and the Basal Ganglia (BG) to achieve this focus called Working Memory (WM). The Working Memory Toolkit (WMtk) was developed based on a computational neuroscience model of this phenomenon with Temporal Difference (TD) Learning for autonomous systems. Recent adaptations of the toolkit either utilize Abstract Task Representations (ATRs…
University of Cambridge（剑桥大学）；Toshiba Europe Limited（东芝欧洲有限公司）
Solving partially-observable Markov decision processes (POMDPs) is critical when applying reinforcement learning to real-world problems, where agents have an incomplete view of the world. We present graph convolutional memory (GCM), the first hybrid memory model for solving POMDPs using reinforcement learning. GCM uses either human-defined or data-driven topological priors to form graph neighborhoods, combining them into a larger network topology using dynamic programming. We query the graph using graph convolution, coalescing relevant memories into a context-dependent belief. When used withou…
Modern analog computing for solving differential and matrix equations
Institute for Artificial Intelligence, School of Integrated Circuits, Peking University, Beijing Advanced Innovation Center for Integrated Circuits（人工智能研究院，集成电路学院，北京大学，北京集成电路先进创新中心）；Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano（电子、信息与生物工程系，米兰理工大学）；IBM Research Europe（IBM欧洲研究院）
Montreal Neurological Institute and Hospital（蒙特利尔神经学研究所与医院）；Sorbonne Universités, UPMC Univ Paris 06（索邦大学，巴黎第六大学（UPMC））；CNRS（法国国家科学研究中心）；University of Lyon（里昂大学）；Université Claude Bernard Lyon 1（里昂第一大学（克洛德·贝尔纳大学））；INSERM（法国国家健康与医学研究院）；Stem Cell and Brain Research Institute U1208（干细胞与脑研究所 U1208）
Accumulating evidence suggest that human behavior in trial-and-error learning tasks based on decisions between discrete actions may involve a combination of reinforcement learning (RL) and working-memory (WM). While the understanding of brain activity at stake in this type of tasks often involve the comparison with non-human primate neurophysiological results, it is not clear whether monkeys use similar combined RL and WM processes to solve these tasks. Here we analyzed the behavior of five monkeys with computational models combining RL and WM. Our model-based analysis approach enables to not …
A major limitation of exact inference algorithms for probabilistic graphical models is their extensive memory usage, which often puts real-world problems out of their reach. In this paper we show how we can extend inference algorithms, particularly Bucket Elimination, a special case of cluster (join) tree decomposition, to utilize disk memory. We provide the underlying ideas and show promising empirical results of exactly solving large problems not solvable before.
Nonlinear Non-Gaussian Density Steering with Input and Noise Channel Mismatch: Sinkhorn with Memory for Solving the Control-affine Schrödinger Bridge Problem
Department of Applied Mathematics, University of California Santa Cruz（加州大学圣克鲁兹分校应用数学系）；Department of Aerospace Engineering, Iowa State University（爱荷华州立大学航空航天工程系）；School of Aerospace Engineering, Georgia Institute of Technology（佐治亚理工学院航空航天工程学院）
Department of Psychology, Rutgers University-New Brunswick（罗格斯大学新不伦瑞克分校心理学系）
Navigating through a visual maze relies on the strategic use of eye movements to select and identify the route. When navigating the maze, there are trade-offs between exploring to the environment and relying on memory. This study examined strategies used to navigating through novel and familiar mazes that were viewed from above and traversed by a mouse cursor. Eye and mouse movements revealed two modes that almost never occurred concurrently: exploration and guidance. Analyses showed that people learned mazes and were able to devise and carry out complex, multi-faceted strategies that traded-o…
An integral function of fully autonomous robots and humans is the ability to focus attention on a few relevant percepts to reach a certain goal while disregarding irrelevant percepts. Humans and animals rely on the interactions between the Pre-Frontal Cortex (PFC) and the Basal Ganglia (BG) to achieve this focus called Working Memory (WM). The Working Memory Toolkit (WMtk) was developed based on a computational neuroscience model of this phenomenon with Temporal Difference (TD) Learning for autonomous systems. Recent adaptations of the toolkit either utilize Abstract Task Representations (ATRs…
Text classification problem is a very broad field of study in the field of natural language processing. In short, the text classification problem is to determine which of the previously determined classes the given text belongs to. Successful studies have been carried out in this field in the past studies. In the study, Bidirectional Encoder Representations for Transformers (BERT), which is a frequently preferred method for solving the classification problem in the field of natural language processing, is used. By solving classification problems through a single model to be used in a chatbot a…
This paper explores the use of Answer Set Programming (ASP) in solving Distributed Constraint Optimization Problems (DCOPs). The paper provides the following novel contributions: (1) It shows how one can formulate DCOPs as logic programs; (2) It introduces ASP-DPOP, the first DCOP algorithm that is based on logic programming; (3) It experimentally shows that ASP-DPOP can be up to two orders of magnitude faster than DPOP (its imperative programming counterpart) as well as solve some problems that DPOP fails to solve, due to memory limitations; and (4) It demonstrates the applicability of ASP in…
Harvard University（哈佛大学）；Harvard College（哈佛学院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）；Harvard Medical School（哈佛医学院）
Continual learning is a problem for artificial neural networks that their biological counterparts are adept at solving. Building on work using Sparse Distributed Memory (SDM) to connect a core neural circuit with the powerful Transformer model, we create a modified Multi-Layered Perceptron (MLP) that is a strong continual learner. We find that every component of our MLP variant translated from biology is necessary for continual learning. Our solution is also free from any memory replay or task information, and introduces novel methods to train sparse networks that may be broadly applicable.
