Search

Grid cells in the medial entorhinal cortex (MEC) of the mammalian brain exhibit a strikingly regular hexagonal firing field over space. These cells are learned after birth and are thought to support spatial navigation but also more abstract computations. Although various computational models, including those based on artificial neural networks, have been proposed to explain the formation of grid cells, the process through which the MEC circuit ${\it learns}$ to develop grid cells remains unclear. In this study, we argue that predictive coding, a biologically plausible plasticity rule known to learn visual representations, can also train neural networks to develop hexagonal grid representations from spatial inputs. We demonstrate that grid cells emerge robustly through predictive coding in both static and dynamic environments, and we develop an understanding of this grid cell learning capability by analytically comparing predictive coding with existing models. Our work therefore offers a novel and biologically plausible perspective on the learning mechanisms underlying grid cells. Moreover, it extends the predictive coding theory to the hippocampal formation, suggesting a unified learning algorithm for diverse cortical representations.

The maximum achievable beam current in an Energy Recovery Linac (ERL) is often constrained by Beam Breakup (BBU) instability. Our previous research highlighted that filling patterns have a substantial impact on BBU instabilities in multi-pass ERLs. In this study, we extend our investigation to the 8-cavity model of the Powerful ERL for Experiment (PERLE). We evaluate its requirements for damping cavity Higher Order Modes (HOMs) and propose optimal filling patterns and bunch timing strategies. Our findings reveal a significant new insight: while filling patterns are crucial, the timing of bunches also plays a critical role in mitigating HOM beam loading and BBU instability. This previously underestimated factor is essential for effective BBU control. We estimated the PERLE threshold current using both analytical and numerical models, incorporating the designed PERLE HOM dampers. During manufacturing, HOM frequencies are expected to vary slightly, with an assumed RMS frequency jitter of 0.001 between cavities for the same HOM. Introducing this jitter into our models, we found that the dampers effectively suppressed BBU instability, achieving a threshold current an order of magnitude higher than the design requirement. Our results offer new insights into ERL BBU beam dynamics and have important implications for the design of future ERLs.

This review paper describes the energy-upgraded CEBAF accelerator. This superconducting linac has achieved 12 GeV beam energy by adding 11 new high-performance cryomodules containing eighty-eight superconducting cavities that have operated CW at an average accelerating gradient of 20 MV/m. After reviewing the attributes and performance of the previous 6 GeV CEBAF accelerator, we discuss the upgraded CEBAF accelerator system in detail with particular attention paid to the new beam acceleration systems. In addition to doubling the acceleration in each linac, the upgrade included improving the beam recirculation magnets, adding more helium cooling capacity to allow the newly installed modules to run cold, adding a new experimental hall, and improving numerous other accelerator components. We review several of the techniques deployed to operate and analyze the accelerator performance, and document system operating experience and performance. In the final portion of the document, we present much of the current planning regarding projects to improve accelerator performance and enhance operating margins, and our plans for ensuring CEBAF operates reliably into the future. For the benefit of potential users of CEBAF, the performance and quality measures for beam delivered to each of the experimental halls is summarized in the appendix., Comment: 66 pages, 73 figures, 21 tables

The International Muon Collider Collaboration (IMCC) [1] was established in 2020 following the recommendations of the European Strategy for Particle Physics (ESPP) and the implementation of the European Strategy for Particle Physics-Accelerator R&D Roadmap by the Laboratory Directors Group [2], hereinafter referred to as the the European LDG roadmap. The Muon Collider Study (MuC) covers the accelerator complex, detectors and physics for a future muon collider. In 2023, European Commission support was obtained for a design study of a muon collider (MuCol) [3]. This project started on 1st March 2023, with work-packages aligned with the overall muon collider studies. In preparation of and during the 2021-22 U.S. Snowmass process, the muon collider project parameters, technical studies and physics performance studies were performed and presented in great detail. Recently, the P5 panel [4] in the U.S. recommended a muon collider R&D, proposed to join the IMCC and envisages that the U.S. should prepare to host a muon collider, calling this their "muon shot". In the past, the U.S. Muon Accelerator Programme (MAP) [5] has been instrumental in studies of concepts and technologies for a muon collider., Comment: This document summarises the International Muon Collider Collaboration (IMCC) progress and status of the Muon Collider R&D programme

In this work, we tackle the problems of efficiency and scalability for predictive coding networks in machine learning. To do so, we first propose a library called PCX, whose focus lies on performance and simplicity, and provides a user-friendly, deep-learning oriented interface. Second, we use PCX to implement a large set of benchmarks for the community to use for their experiments. As most works propose their own tasks and architectures, do not compare one against each other, and focus on small-scale tasks, a simple and fast open-source library adopted by the whole community would address all of these concerns. Third, we perform extensive benchmarks using multiple algorithms, setting new state-of-the-art results in multiple tasks and datasets, as well as highlighting limitations inherent to PC that should be addressed. Thanks to the efficiency of PCX, we are able to analyze larger architectures than commonly used, providing baselines to galvanize community efforts towards one of the main open problems in the field: scalability. The code for PCX is available at \textit{https://github.com/liukidar/pcax}., Comment: 33 pages, 25 figures

An autoassociative memory model is a function that, given a set of data points, takes as input an arbitrary vector and outputs the most similar data point from the memorized set. However, popular memory models fail to retrieve images even when the corruption is mild and easy to detect for a human evaluator. This is because similarities are evaluated in the raw pixel space, which does not contain any semantic information about the images. This problem can be easily solved by computing \emph{similarities} in an embedding space instead of the pixel space. We show that an effective way of computing such embeddings is via a network pretrained with a contrastive loss. As the dimension of embedding spaces is often significantly smaller than the pixel space, we also have a faster computation of similarity scores. We test this method on complex datasets such as CIFAR10 and STL10. An additional drawback of current models is the need of storing the whole dataset in the pixel space, which is often extremely large. We relax this condition and propose a class of memory models that only stores low-dimensional semantic embeddings, and uses them to retrieve similar, but not identical, memories. We demonstrate a proof of concept of this method on a simple task on the MNIST dataset., Comment: 8 Pages, 4 Figures, accepted for publication at ECAI 2023

This document presents the initial scientific case for upgrading the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab (JLab) to 22 GeV. It is the result of a community effort, incorporating insights from a series of workshops conducted between March 2022 and April 2023. With a track record of over 25 years in delivering the world's most intense and precise multi-GeV electron beams, CEBAF's potential for a higher energy upgrade presents a unique opportunity for an innovative nuclear physics program, which seamlessly integrates a rich historical background with a promising future. The proposed physics program encompass a diverse range of investigations centered around the nonperturbative dynamics inherent in hadron structure and the exploration of strongly interacting systems. It builds upon the exceptional capabilities of CEBAF in high-luminosity operations, the availability of existing or planned Hall equipment, and recent advancements in accelerator technology. The proposed program cover various scientific topics, including Hadron Spectroscopy, Partonic Structure and Spin, Hadronization and Transverse Momentum, Spatial Structure, Mechanical Properties, Form Factors and Emergent Hadron Mass, Hadron-Quark Transition, and Nuclear Dynamics at Extreme Conditions, as well as QCD Confinement and Fundamental Symmetries. Each topic highlights the key measurements achievable at a 22 GeV CEBAF accelerator. Furthermore, this document outlines the significant physics outcomes and unique aspects of these programs that distinguish them from other existing or planned facilities. In summary, this document provides an exciting rationale for the energy upgrade of CEBAF to 22 GeV, outlining the transformative scientific potential that lies within reach, and the remarkable opportunities it offers for advancing our understanding of hadron physics and related fundamental phenomena., Comment: Updates to the list of authors; Preprint number changed from theory to experiment; Updates to sections 4 and 6, including additional figures

Forming accurate memory of sequential stimuli is a fundamental function of biological agents. However, the computational mechanism underlying sequential memory in the brain remains unclear. Inspired by neuroscience theories and recent successes in applying predictive coding (PC) to \emph{static} memory tasks, in this work we propose a novel PC-based model for \emph{sequential} memory, called \emph{temporal predictive coding} (tPC). We show that our tPC models can memorize and retrieve sequential inputs accurately with a biologically plausible neural implementation. Importantly, our analytical study reveals that tPC can be viewed as a classical Asymmetric Hopfield Network (AHN) with an implicit statistical whitening process, which leads to more stable performance in sequential memory tasks of structured inputs. Moreover, we find that tPC exhibits properties consistent with behavioral observations and theories in neuroscience, thereby strengthening its biological relevance. Our work establishes a possible computational mechanism underlying sequential memory in the brain that can also be theoretically interpreted using existing memory model frameworks., Comment: 37th Conference on Neural Information Processing Systems (NeurIPS 2023)

This White Paper presents the community inputs and scientific conclusions from the Hot and Cold QCD Town Meeting that took place September 23-25, 2022 at MIT, as part of the Nuclear Science Advisory Committee (NSAC) 2023 Long Range Planning process. A total of 424 physicists registered for the meeting. The meeting highlighted progress in Quantum Chromodynamics (QCD) nuclear physics since the 2015 LRP (LRP15) and identified key questions and plausible paths to obtaining answers to those questions, defining priorities for our research over the coming decade. In defining the priority of outstanding physics opportunities for the future, both prospects for the short (~ 5 years) and longer term (5-10 years and beyond) are identified together with the facilities, personnel and other resources needed to maximize the discovery potential and maintain United States leadership in QCD physics worldwide. This White Paper is organized as follows: In the Executive Summary, we detail the Recommendations and Initiatives that were presented and discussed at the Town Meeting, and their supporting rationales. Section 2 highlights major progress and accomplishments of the past seven years. It is followed, in Section 3, by an overview of the physics opportunities for the immediate future, and in relation with the next QCD frontier: the EIC. Section 4 provides an overview of the physics motivations and goals associated with the EIC. Section 5 is devoted to the workforce development and support of diversity, equity and inclusion. This is followed by a dedicated section on computing in Section 6. Section 7 describes the national need for nuclear data science and the relevance to QCD research., Comment: QCD Town Meeting White Paper, as submitted to 2023 NSAC LRP committee on Feb. 28, 2023

Predictive coding networks are neuroscience-inspired models with roots in both Bayesian statistics and neuroscience. Training such models, however, is quite inefficient and unstable. In this work, we show how by simply changing the temporal scheduling of the update rule for the synaptic weights leads to an algorithm that is much more efficient and stable than the original one, and has theoretical guarantees in terms of convergence. The proposed algorithm, that we call incremental predictive coding (iPC) is also more biologically plausible than the original one, as it it fully automatic. In an extensive set of experiments, we show that iPC constantly performs better than the original formulation on a large number of benchmarks for image classification, as well as for the training of both conditional and masked language models, in terms of test accuracy, efficiency, and convergence with respect to a large set of hyperparameters., Comment: Change of title and abstract, that now reflect the version accepted for publication. One co-author also added, that performed the additional experiments

The coupling of transverse motion is a natural occurrence in particle accelerators, either in the form of a residual coupling arising from imperfections or originating by design from strong systematic coupling fields. While the first can be treated perturbatively, the latter requires a robust approach adapted to strongly coupled optics and a parametrization of the linear optics must be performed to explore beam dynamics in such peculiar lattices. This paper reviews the main concepts commonly put forth to describe coupled optics and clarifies the proposed parametrization formalisms. The links between the generalized Twiss parameters used by the different approaches are formally proven, and their physical interpretations are highlighted. The analytical methods have been implemented in a reference Python package and connected with a ray-tracing code to explore strongly coupled lattices featuring complex 3D fields. Multiple examples are discussed in detail to highlight the key physical interpretations of the parametrizations and characteristics of the lattices., Comment: 33 pages, 17 figures, to be published in Physical Review Accelerators and Beams (PRAB)

Predictive coding (PC) is an influential theory in computational neuroscience, which argues that the cortex forms unsupervised world models by implementing a hierarchical process of prediction error minimization. PC networks (PCNs) are trained in two phases. First, neural activities are updated to optimize the network's response to external stimuli. Second, synaptic weights are updated to consolidate this change in activity -- an algorithm called \emph{prospective configuration}. While previous work has shown how in various limits, PCNs can be found to approximate backpropagation (BP), recent work has demonstrated that PCNs operating in this standard regime, which does not approximate BP, nevertheless obtain competitive training and generalization performance to BP-trained networks while outperforming them on tasks such as online, few-shot, and continual learning, where brains are known to excel. Despite this promising empirical performance, little is understood theoretically about the properties and dynamics of PCNs in this regime. In this paper, we provide a comprehensive theoretical analysis of the properties of PCNs trained with prospective configuration. We first derive analytical results concerning the inference equilibrium for PCNs and a previously unknown close connection relationship to target propagation (TP). Secondly, we provide a theoretical analysis of learning in PCNs as a variant of generalized expectation-maximization and use that to prove the convergence of PCNs to critical points of the BP loss function, thus showing that deep PCNs can, in theory, achieve the same generalization performance as BP, while maintaining their unique advantages., Comment: 21/07/22 initial upload (finally); 03/08/22 revisions

Energy-recovery linacs (ERLs) have been emphasised by the recent (2020) update of the European Strategy for Particle Physics as one of the most promising technologies for the accelerator base of future high-energy physics. The current paper has been written as a base document to support and specify details of the recently published European roadmap for the development of energy-recovery linacs. The paper summarises the previous achievements on ERLs and the status of the field and its basic technology items. The main possible future contributions and applications of ERLs to particle and nuclear physics as well as industrial developments are presented. The paper includes a vision for the further future, beyond 2030, as well as a comparative data base for the main existing and forthcoming ERL facilities. A series of continuous innovations, such as on intense electron sources or high-quality superconducting cavity technology, will massively contribute to the development of accelerator physics at large. Industrial applications are potentially revolutionary and may carry the development of ERLs much further, establishing another shining example of the impact of particle physics on society and its technical foundation with a special view on sustaining nature.

The LHeC provides an intense, high energy electron beam to collide with the LHC. It represents the highest energy application of energy recovery linac (ERL) technology which is increasingly recognized as one of the major pilot technologies for the development of particle physics because it utilizes and stimulates superconducting RF technology progress, and it increases intensity while keeping the power consumption low. The LHeC instantaneous luminosity is determined through the integrated luminosity goal. The electron beam energy is chosen to achieve TeV cms collision energy and enable competitive searches and precision Higgs boson measurements. The wall-plug power has been constrained to 100 MW. Two super-conducting linacs of about 900 m length, which are placed opposite to each other, accelerate the passing electrons by 8.3 GeV each. This leads to a final electron beam energy of about 50 GeV in a 3-turn racetrack energy recovery linac configuration., Comment: arXiv admin note: substantial text overlap with arXiv:2007.14491

How the brain performs credit assignment is a fundamental unsolved problem in neuroscience. Many `biologically plausible' algorithms have been proposed, which compute gradients that approximate those computed by backpropagation (BP), and which operate in ways that more closely satisfy the constraints imposed by neural circuitry. Many such algorithms utilize the framework of energy-based models (EBMs), in which all free variables in the model are optimized to minimize a global energy function. However, in the literature, these algorithms exist in isolation and no unified theory exists linking them together. Here, we provide a comprehensive theory of the conditions under which EBMs can approximate BP, which lets us unify many of the BP approximation results in the literature (namely, predictive coding, equilibrium propagation, and contrastive Hebbian learning) and demonstrate that their approximation to BP arises from a simple and general mathematical property of EBMs at free-phase equilibrium. This property can then be exploited in different ways with different energy functions, and these specific choices yield a family of BP-approximating algorithms, which both includes the known results in the literature and can be used to derive new ones., Comment: 31/05/22 initial upload; 22/06/22 change corresponding author; 03/08/22 revisions

Neutrino factories, neutrino beams produced in the decay of a muon or antimuon beam inside a storage ring, yield cleaner, richer, and more flexible neutrino beams relative to super-beams. We explore the physics case for this type of beam both for standard oscillation as well as new physics searches and present some machine options. We argue that there is a rich program beyond what the current neutrino program can cover and a string synergy with the muon collider program., Comment: 32 pages, 4 figures. White paper contribution to Snowmass 2021

The backpropagation of error algorithm used to train deep neural networks has been fundamental to the successes of deep learning. However, it requires sequential backward updates and non-local computations, which make it challenging to parallelize at scale and is unlike how learning works in the brain. Neuroscience-inspired learning algorithms, however, such as \emph{predictive coding}, which utilize local learning, have the potential to overcome these limitations and advance beyond current deep learning technologies. While predictive coding originated in theoretical neuroscience as a model of information processing in the cortex, recent work has developed the idea into a general-purpose algorithm able to train neural networks using only local computations. In this survey, we review works that have contributed to this perspective and demonstrate the close theoretical connections between predictive coding and backpropagation, as well as works that highlight the multiple advantages of using predictive coding models over backpropagation-trained neural networks. Specifically, we show the substantially greater flexibility of predictive coding networks against equivalent deep neural networks, which can function as classifiers, generators, and associative memories simultaneously, and can be defined on arbitrary graph topologies. Finally, we review direct benchmarks of predictive coding networks on machine learning classification tasks, as well as its close connections to control theory and applications in robotics., Comment: 18/02/22 initial upload

A large number of neural network models of associative memory have been proposed in the literature. These include the classical Hopfield networks (HNs), sparse distributed memories (SDMs), and more recently the modern continuous Hopfield networks (MCHNs), which possesses close links with self-attention in machine learning. In this paper, we propose a general framework for understanding the operation of such memory networks as a sequence of three operations: similarity, separation, and projection. We derive all these memory models as instances of our general framework with differing similarity and separation functions. We extend the mathematical framework of Krotov et al (2020) to express general associative memory models using neural network dynamics with only second-order interactions between neurons, and derive a general energy function that is a Lyapunov function of the dynamics. Finally, using our framework, we empirically investigate the capacity of using different similarity functions for these associative memory models, beyond the dot product similarity measure, and demonstrate empirically that Euclidean or Manhattan distance similarity metrics perform substantially better in practice on many tasks, enabling a more robust retrieval and higher memory capacity than existing models., Comment: 09/02/22 initial upload; 17/06/222 camera ready version upload

Training with backpropagation (BP) in standard deep learning consists of two main steps: a forward pass that maps a data point to its prediction, and a backward pass that propagates the error of this prediction back through the network. This process is highly effective when the goal is to minimize a specific objective function. However, it does not allow training on networks with cyclic or backward connections. This is an obstacle to reaching brain-like capabilities, as the highly complex heterarchical structure of the neural connections in the neocortex are potentially fundamental for its effectiveness. In this paper, we show how predictive coding (PC), a theory of information processing in the cortex, can be used to perform inference and learning on arbitrary graph topologies. We experimentally show how this formulation, called PC graphs, can be used to flexibly perform different tasks with the same network by simply stimulating specific neurons, and investigate how the topology of the graph influences the final performance. We conclude by comparing against simple baselines trained~with~BP., Comment: 15 pages, 11 figures

The 2020 update of the European Strategy for Particle Physics emphasised the importance of an intensified and well-coordinated programme of accelerator R&D, supporting the design and delivery of future particle accelerators in a timely, affordable and sustainable way. This report sets out a roadmap for European accelerator R&D for the next five to ten years, covering five topical areas identified in the Strategy update. The R&D objectives include: improvement of the performance and cost-performance of magnet and radio-frequency acceleration systems; investigations of the potential of laser / plasma acceleration and energy-recovery linac techniques; and development of new concepts for muon beams and muon colliders. The goal of the roadmap is to document the collective view of the field on the next steps for the R&D programme, and to provide the evidence base to support subsequent decisions on prioritisation, resourcing and implementation., Comment: 270 pages, 58 figures. Editor: N. Mounet. LDG chair: D. Newbold. Panel chairs: P. V\'edrine (HFM), S. Bousson (RF), R. Assmann (plasma), D. Schulte (muon), M. Klein (ERL). Panel editors: B. Baudouy (HFM), L. Bottura (HFM), S. Bousson (RF), G. Burt (RF), R. Assmann (plasma), E. Gschwendtner (plasma), R. Ischebeck (plasma), C. Rogers (muon), D. Schulte (muon), M. Klein (ERL)

Novel considerations are presented on the physics, apparatus and accelerator designs for a future, luminous, energy frontier electron-hadron ($eh$) scattering experiment at the LHC in the thirties for which key physics topics and their relation to the hadron-hadron HL-LHC physics programme are discussed. Demands are derived set by these physics topics on the design of the LHeC detector, a corresponding update of which is described. Optimisations on the accelerator design, especially the interaction region (IR), are presented. Initial accelerator considerations indicate that a common IR is possible to be built which alternately could serve $eh$ and $hh$ collisions while other experiments would stay on $hh$ in either condition. A forward-backward symmetrised option of the LHeC detector is sketched which would permit extending the LHeC physics programme to also include aspects of hadron-hadron physics. The vision of a joint $eh$ and $hh$ physics experiment is shown to open new prospects for solving fundamental problems of high energy heavy-ion physics including the partonic structure of nuclei and the emergence of hydrodynamics in quantum field theory while the genuine TeV scale DIS physics is of unprecedented rank., Comment: 27 pages, 24 figures, 6 tables; to appear in Eur. Phys. J. C

We summarize the ongoing scientific program of the 12 GeV Continuous Electron Beam Accelerator Facility (CEBAF) and give an outlook into future scientific opportunities. The program addresses important topics in nuclear, hadronic, and electroweak physics including nuclear femtography, meson and baryon spectroscopy, quarks and gluons in nuclei, precision tests of the standard model, and dark sector searches. Potential upgrades of CEBAF are considered, such as higher luminosity, polarized and unpolarized positron beams, and doubling the beam energy., Comment: To be published by Progress in Particle and Nuclear Physics in 2022