搜索结果：Learning & memory (Cold Spring Harbor, N.Y.)

Large language models remain limited as continual learning systems, motivating renewed interest in Sparse Distributed Memory (SDM) as an explicit online episodic memory. CALM (Nechesov and Ruponen, 2025) identifies its threshold-binary encoder as an open design question. This paper evaluates rank-order N-of-M encoding (Furber et al., 2007) as an alternative. We make three contributions. First, a faithful reimplementation validates the published architecture by confirming exact equivalence between WheelSDM and RankOrderSDM (cosine similarity 1.0000 across 10 seeds) and reproducing the documented divergence of RDLIF neurons under interference. Second, multi-seed capacity experiments show RankOrderSDM outperforming StandardSDM by 13.4 percentage points at saturation in the scaled configuration and by 0.8 percentage points at the published architecture scale. Third, BER robustness experiments disentangle representation and learning effects, showing that the large robustness gain arises primarily from the interaction of rank-order encoding with MAX-Hebbian learning, while the encoder alone provides only a small advantage under matched learning conditions. Experiments on GloVe-100 embedd

The promise of learning to learn for robotics rests on the hope that by extracting some information about the learning process itself we can speed up subsequent similar learning tasks. Here, we introduce a computationally efficient online meta-learning algorithm that builds and optimizes a memory model of the optimal learning rate landscape from previously observed gradient behaviors. While performing task specific optimization, this memory of learning rates predicts how to scale currently observed gradients. After applying the gradient scaling our meta-learner updates its internal memory based on the observed effect its prediction had. Our meta-learner can be combined with any gradient-based optimizer, learns on the fly and can be transferred to new optimization tasks. In our evaluations we show that our meta-learning algorithm speeds up learning of MNIST classification and a variety of learning control tasks, either in batch or online learning settings.

Deep learning typically requires training a very capable architecture using large datasets. However, many important learning problems demand an ability to draw valid inferences from small size datasets, and such problems pose a particular challenge for deep learning. In this regard, various researches on "meta-learning" are being actively conducted. Recent work has suggested a Memory Augmented Neural Network (MANN) for meta-learning. MANN is an implementation of a Neural Turing Machine (NTM) with the ability to rapidly assimilate new data in its memory, and use this data to make accurate predictions. In models such as MANN, the input data samples and their appropriate labels from previous step are bound together in the same memory locations. This often leads to memory interference when performing a task as these models have to retrieve a feature of an input from a certain memory location and read only the label information bound to that location. In this paper, we tried to address this issue by presenting a more robust MANN. We revisited the idea of meta-learning and proposed a new memory augmented neural network by explicitly splitting the external memory into feature and label me

Embedding learning, a.k.a. representation learning, has been shown to be able to model large-scale semantic knowledge graphs. A key concept is a mapping of the knowledge graph to a tensor representation whose entries are predicted by models using latent representations of generalized entities. Latent variable models are well suited to deal with the high dimensionality and sparsity of typical knowledge graphs. In recent publications the embedding models were extended to also consider time evolutions, time patterns and subsymbolic representations. In this paper we map embedding models, which were developed purely as solutions to technical problems for modelling temporal knowledge graphs, to various cognitive memory functions, in particular to semantic and concept memory, episodic memory, sensory memory, short-term memory, and working memory. We discuss learning, query answering, the path from sensory input to semantic decoding, and the relationship between episodic memory and semantic memory. We introduce a number of hypotheses on human memory that can be derived from the developed mathematical models.

Sequential learning with Gaussian processes (GPs) is challenging when access to past data is limited, for example, in continual and active learning. In such cases, errors can accumulate over time due to inaccuracies in the posterior, hyperparameters, and inducing points, making accurate learning challenging. Here, we present a method to keep all such errors in check using the recently proposed dual sparse variational GP. Our method enables accurate inference for generic likelihoods and improves learning by actively building and updating a memory of past data. We demonstrate its effectiveness in several applications involving Bayesian optimization, active learning, and continual learning.

Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledge. Continual fine-tuning and in-context learning are costly and brittle, whereas neural memory methods promise lightweight updates with minimal forgetting. However, existing neural memory models typically assume a single fixed objective and homogeneous information streams, leaving users with no control over what the model remembers or ignores over time. To address this challenge, we propose a generalized neural memory system that performs flexible updates based on learning instructions specified in natural language. Our approach enables adaptive agents to learn selectively from heterogeneous information sources, supporting settings, such as healthcare and customer service, where fixed-objective memory updates are insufficient.

Learning curves are a concept from social sciences that has been adopted in the context of machine learning to assess the performance of a learning algorithm with respect to a certain resource, e.g., the number of training examples or the number of training iterations. Learning curves have important applications in several machine learning contexts, most notably in data acquisition, early stopping of model training, and model selection. For instance, learning curves can be used to model the performance of the combination of an algorithm and its hyperparameter configuration, providing insights into their potential suitability at an early stage and often expediting the algorithm selection process. Various learning curve models have been proposed to use learning curves for decision making. Some of these models answer the binary decision question of whether a given algorithm at a certain budget will outperform a certain reference performance, whereas more complex models predict the entire learning curve of an algorithm. We contribute a framework that categorises learning curve approaches using three criteria: the decision-making situation they address, the intrinsic learning curve ques

A key challenge for machine intelligence is to learn new visual concepts without forgetting the previously acquired knowledge. Continual learning is aimed towards addressing this challenge. However, there is a gap between existing supervised continual learning and human-like intelligence, where human is able to learn from both labeled and unlabeled data. How unlabeled data affects learning and catastrophic forgetting in the continual learning process remains unknown. To explore these issues, we formulate a new semi-supervised continual learning method, which can be generically applied to existing continual learning models. Specifically, a novel gradient learner learns from labeled data to predict gradients on unlabeled data. Hence, the unlabeled data could fit into the supervised continual learning method. Different from conventional semi-supervised settings, we do not hypothesize that the underlying classes, which are associated to the unlabeled data, are known to the learning process. In other words, the unlabeled data could be very distinct from the labeled data. We evaluate the proposed method on mainstream continual learning, adversarial continual learning, and semi-supervised

Dendritic spines, the carriers of long-term memory, occupy a small fraction of cortical space, and yet they are the major consumers of brain metabolic energy. What fraction of this energy goes for synaptic plasticity, correlated with learning and memory? It is estimated here based on neurophysiological and proteomic data for rat brain that, depending on the level of protein phosphorylation, the energy cost of synaptic plasticity constitutes a small fraction of the energy used for fast excitatory synaptic transmission, typically $4.0-11.2 \%$. Next, this study analyzes a metabolic cost of a new learning and its memory trace in relation to the cost of prior memories, using a class of cascade models of synaptic plasticity. It is argued that these models must contain bidirectional cyclic motifs, related to protein phosphorylation, to be compatible with basic thermodynamic principles. For most investigated parameters longer memories generally require proportionally more energy to store. The exception are the parameters controlling the speed of molecular transitions (e.g. ATP driven phosphorylation rate), for which memory lifetime per invested energy can increase progressively for longer

We propose a framework that amortizes the cost of inference-time reasoning by converting transient critiques into retrievable guidelines, through a file-based memory system and agent-controlled tool calls. We evaluate this method on the Rubric Feedback Bench, a novel dataset for rubric-based learning. Experiments demonstrate that our augmented LLMs rapidly match the performance of test-time refinement pipelines while drastically reducing inference cost.

Online active learning is a paradigm in machine learning that aims to select the most informative data points to label from a data stream. The problem of minimizing the cost associated with collecting labeled observations has gained a lot of attention in recent years, particularly in real-world applications where data is only available in an unlabeled form. Annotating each observation can be time-consuming and costly, making it difficult to obtain large amounts of labeled data. To overcome this issue, many active learning strategies have been proposed in the last decades, aiming to select the most informative observations for labeling in order to improve the performance of machine learning models. These approaches can be broadly divided into two categories: static pool-based and stream-based active learning. Pool-based active learning involves selecting a subset of observations from a closed pool of unlabeled data, and it has been the focus of many surveys and literature reviews. However, the growing availability of data streams has led to an increase in the number of approaches that focus on online active learning, which involves continuously selecting and labeling observations as

Recently, neuro-inspired episodic control (EC) methods have been developed to overcome the data-inefficiency of standard deep reinforcement learning approaches. Using non-/semi-parametric models to estimate the value function, they learn rapidly, retrieving cached values from similar past states. In realistic scenarios, with limited resources and noisy data, maintaining meaningful representations in memory is essential to speed up the learning and avoid catastrophic forgetting. Unfortunately, EC methods have a large space and time complexity. We investigate different solutions to these problems based on prioritising and ranking stored states, as well as online clustering techniques. We also propose a new dynamic online k-means algorithm that is both computationally-efficient and yields significantly better performance at smaller memory sizes; we validate this approach on classic reinforcement learning environments and Atari games.

A novel approach to learning is presented, combining features of on-line and off-line methods to achieve considerable performance in the task of learning a backgammon value function in a process that exploits the processing power of parallel supercomputers. The off-line methods comprise a set of techniques for parallelizing neural network training and $TD(λ)$ reinforcement learning; here Monte-Carlo ``Rollouts'' are introduced as a massively parallel on-line policy improvement technique which applies resources to the decision points encountered during the search of the game tree to further augment the learned value function estimate. A level of play roughly as good as, or possibly better than, the current champion human and computer backgammon players has been achieved in a short period of learning.

Continual Learning (CL) is an emerging machine learning paradigm that aims to learn from a continuous stream of tasks without forgetting knowledge learned from the previous tasks. To avoid performance decrease caused by forgetting, prior studies exploit episodic memory (EM), which stores a subset of the past observed samples while learning from new non-i.i.d. data. Despite the promising results, since CL is often assumed to execute on mobile or IoT devices, the EM size is bounded by the small hardware memory capacity and makes it infeasible to meet the accuracy requirements for real-world applications. Specifically, all prior CL methods discard samples overflowed from the EM and can never retrieve them back for subsequent training steps, incurring loss of information that would exacerbate catastrophic forgetting. We explore a novel hierarchical EM management strategy to address the forgetting issue. In particular, in mobile and IoT devices, real-time data can be stored not just in high-speed RAMs but in internal storage devices as well, which offer significantly larger capacity than the RAMs. Based on this insight, we propose to exploit the abundant storage to preserve past experie

Contrastive learning operates on a simple yet effective principle: Embeddings of positive pairs are pulled together, while those of negative pairs are pushed apart. In this paper, we propose a unified framework for understanding contrastive learning through the lens of cosine similarity, and present two key theoretical insights derived from this framework. First, in full-batch settings, we show that perfect alignment of positive pairs is unattainable when negative-pair similarities fall below a threshold, and this misalignment can be mitigated by incorporating within-view negative pairs into the objective. Second, in mini-batch settings, smaller batch sizes induce stronger separation among negative pairs in the embedding space, i.e., higher variance in their similarities, which in turn degrades the quality of learned representations compared to full-batch settings. To address this, we propose an auxiliary loss that reduces the variance of negative-pair similarities in mini-batch settings. Empirical results show that incorporating the proposed loss improves performance in small-batch settings.

We consider multi-armed bandit problems in social groups wherein each individual has bounded memory and shares the common goal of learning the best arm/option. We say an individual learns the best option if eventually (as $t \to \infty$) it pulls only the arm with the highest average reward. While this goal is provably impossible for an isolated individual, we show that, in social groups, this goal can be achieved easily with the aid of social persuasion, i.e., communication. Specifically, we study the learning dynamics wherein an individual sequentially decides on which arm to pull next based on not only its private reward feedback but also the suggestions provided by randomly chosen peers. Our learning dynamics are hard to analyze via explicit probabilistic calculations due to the stochastic dependency induced by social interaction. Instead, we employ the mean-field approximation method from statistical physics and we show: (1) With probability $\to 1$ as the social group size $N \to \infty $, every individual in the social group learns the best option. (2) Over an arbitrary finite time horizon $[0, T]$, with high probability (in $N$), the fraction of individuals that prefer the

Deep reinforcement learning algorithms have recently been used to train multiple interacting agents in a centralised manner whilst keeping their execution decentralised. When the agents can only acquire partial observations and are faced with tasks requiring coordination and synchronisation skills, inter-agent communication plays an essential role. In this work, we propose a framework for multi-agent training using deep deterministic policy gradients that enables concurrent, end-to-end learning of an explicit communication protocol through a memory device. During training, the agents learn to perform read and write operations enabling them to infer a shared representation of the world. We empirically demonstrate that concurrent learning of the communication device and individual policies can improve inter-agent coordination and performance in small-scale systems. Our experimental results show that the proposed method achieves superior performance in scenarios with up to six agents. We illustrate how different communication patterns can emerge on six different tasks of increasing complexity. Furthermore, we study the effects of corrupting the communication channel, provide a visuali

The success of federated learning (FL) ultimately depends on how strategic participants behave under partial observability, yet most formulations still treat FL as a static optimization problem. We instead view FL deployments as governed strategic systems and develop an analytical framework that separates welfare-improving behavior from metric gaming. Within this framework, we introduce indices that quantify manipulability, the price of gaming, and the price of cooperation, and we use them to study how rules, information disclosure, evaluation metrics, and aggregator-switching policies reshape incentives and cooperation patterns. We derive threshold conditions for deterring harmful gaming while preserving benign cooperation, and for triggering auto-switch rules when early-warning indicators become critical. Building on these results, we construct a design toolkit including a governance checklist and a simple audit-budget allocation algorithm with a provable performance guarantee. Simulations across diverse stylized environments and a federated learning case study consistently match the qualitative and quantitative patterns predicted by our framework. Taken together, our results pro

A common belief is that intrinsically interpretable deep learning models ensure a correct, intuitive understanding of their behavior and offer greater robustness against accidental errors or intentional manipulation. However, these beliefs have not been comprehensively verified, and growing evidence casts doubt on them. In this paper, we highlight the risks related to overreliance and susceptibility to adversarial manipulation of these so-called "intrinsically (aka inherently) interpretable" models by design. We introduce two strategies for adversarial analysis with prototype manipulation and backdoor attacks against prototype-based networks, and discuss how concept bottleneck models defend against these attacks. Fooling the model's reasoning by exploiting its use of latent prototypes manifests the inherent uninterpretability of deep neural networks, leading to a false sense of security reinforced by a visual confirmation bias. The reported limitations of part-prototype networks put their trustworthiness and applicability into question, motivating further work on the robustness and alignment of (deep) interpretable models.