像人类一样自然而然地处理和保留新信息的能力是在训练神经网络时受到极大追捧的壮举。不幸的是，传统优化算法通常需要在培训时间和更新WRT期间可用的大量数据。培训过程完成后，新数据很难。实际上，当出现新数据或任务时，由于神经网络容易遭受灾难性遗忘，因此可能会丢失先前的进展。灾难性遗忘描述了当神经网络在获得新信息时完全忘记以前的知识时，这种现象。我们提出了一种新颖的培训算法，称为培训，通过解释我们利用层面相关性传播的方式，以保留神经网络在培训新数据时已经在先前任务中学习的信息。该方法在一系列基准数据集以及更复杂的数据上进行评估。我们的方法不仅成功地保留了神经网络中旧任务的知识，而且比其他最先进的解决方案更有效地进行了资源。

可解释的人工智能（XAI）的新兴领域旨在为当今强大但不透明的深度学习模型带来透明度。尽管本地XAI方法以归因图的形式解释了个体预测，从而确定了重要特征的发生位置（但没有提供有关其代表的信息），但全局解释技术可视化模型通常学会的编码的概念。因此，两种方法仅提供部分见解，并留下将模型推理解释的负担。只有少数当代技术旨在将本地和全球XAI背后的原则结合起来，以获取更多信息的解释。但是，这些方法通常仅限于特定的模型体系结构，或对培训制度或数据和标签可用性施加其他要求，这实际上使事后应用程序成为任意预训练的模型。在这项工作中，我们介绍了概念相关性传播方法（CRP）方法，该方法结合了XAI的本地和全球观点，因此允许回答“何处”和“ where”和“什么”问题，而没有其他约束。我们进一步介绍了相关性最大化的原则，以根据模型对模型的有用性找到代表性的示例。因此，我们提高了对激活最大化及其局限性的共同实践的依赖。我们证明了我们方法在各种环境中的能力，展示了概念相关性传播和相关性最大化导致了更加可解释的解释，并通过概念图表，概念组成分析和概念集合和概念子区和概念子区和概念子集和定量研究对模型的表示和推理提供了深刻的见解。它们在细粒度决策中的作用。

Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning capabilities. In this paper, we propose a task-based hard attention mechanism that preserves previous tasks' information without affecting the current task's learning. A hard attention mask is learned concurrently to every task, through stochastic gradient descent, and previous masks are exploited to condition such learning. We show that the proposed mechanism is effective for reducing catastrophic forgetting, cutting current rates by 45 to 80%. We also show that it is robust to different hyperparameter choices, and that it offers a number of monitoring capabilities. The approach features the possibility to control both the stability and compactness of the learned knowledge, which we believe makes it also attractive for online learning or network compression applications.

Continual Learning (CL) is a field dedicated to devise algorithms able to achieve lifelong learning. Overcoming the knowledge disruption of previously acquired concepts, a drawback affecting deep learning models and that goes by the name of catastrophic forgetting, is a hard challenge. Currently, deep learning methods can attain impressive results when the data modeled does not undergo a considerable distributional shift in subsequent learning sessions, but whenever we expose such systems to this incremental setting, performance drop very quickly. Overcoming this limitation is fundamental as it would allow us to build truly intelligent systems showing stability and plasticity. Secondly, it would allow us to overcome the onerous limitation of retraining these architectures from scratch with the new updated data. In this thesis, we tackle the problem from multiple directions. In a first study, we show that in rehearsal-based techniques (systems that use memory buffer), the quantity of data stored in the rehearsal buffer is a more important factor over the quality of the data. Secondly, we propose one of the early works of incremental learning on ViTs architectures, comparing functional, weight and attention regularization approaches and propose effective novel a novel asymmetric loss. At the end we conclude with a study on pretraining and how it affects the performance in Continual Learning, raising some questions about the effective progression of the field. We then conclude with some future directions and closing remarks.

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries. Our main contributions concern (1) a taxonomy and extensive overview of the state-of-the-art; (2) a novel framework to continually determine the stability-plasticity trade-off of the continual learner; (3) a comprehensive experimental comparison of 11 state-of-the-art continual learning methods and 4 baselines. We empirically scrutinize method strengths and weaknesses on three benchmarks, considering Tiny Imagenet and large-scale unbalanced iNaturalist and a sequence of recognition datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time and storage.

除了机器学习（ML）模型的令人印象深刻的预测力外，最近还出现了解释方法，使得能够解释诸如深神经网络的复杂非线性学习模型。获得更好的理解尤其重要。对于安全 - 关键的ML应用或医学诊断等。虽然这种可解释的AI（XAI）技术对分类器达到了重大普及，但到目前为止对XAI的重点进行了很少的关注（Xair）。在这篇综述中，我们澄清了XAI对回归和分类任务的基本概念差异，为Xair建立了新的理论见解和分析，为Xair提供了真正的实际回归问题的示范，最后讨论了该领域仍然存在的挑战。

在持续学习中使用神经网络中的任务特定组件（CL）是一种令人信服的策略，可以解决固定容量模型中稳定性 - 塑性困境，而无需访问过去的数据。当前方法仅着重于选择一个新任务的子网络，以减少忘记过去任务。但是，这种选择可能会限制有助于将来学习的相关过去知识的前瞻性转移。我们的研究表明，当统一的分类器用于所有类别的任务课程学习（class-il）时，共同满足这两个目标是更具挑战性的，因为这很容易跨越任务之间的类之间的歧义。此外，当跨任务的课程相似性增加时，挑战就会增加。为了应对这一挑战，我们提出了一种名为AFAF的新CL方法，旨在避免忘记并允许使用Fix-apainality模型在IL类中向前转移。 AFAF分配了一个子网络，该子网络可以选择性地转移相关知识到新任务，同时保留过去的知识，重复一些先前分配的组件以利用固定容量，并在存在相似之处时解决类型。该实验表明，AFAF在为模型提供多种CL所需属性方面的有效性，同时在具有不同语义相似性的各种具有挑战性的基准上优于最先进的方法。

增量任务学习（ITL）是一个持续学习的类别，试图培训单个网络以进行多个任务（一个接一个），其中每个任务的培训数据仅在培训该任务期间可用。当神经网络接受较新的任务培训时，往往会忘记旧任务。该特性通常被称为灾难性遗忘。为了解决此问题，ITL方法使用情节内存，参数正则化，掩盖和修剪或可扩展的网络结构。在本文中，我们提出了一个基于低级别分解的新的增量任务学习框架。特别是，我们表示每一层的网络权重作为几个等级1矩阵的线性组合。为了更新新任务的网络，我们学习一个排名1（或低级别）矩阵，并将其添加到每一层的权重。我们还引入了一个其他选择器向量，该向量将不同的权重分配给对先前任务的低级矩阵。我们表明，就准确性和遗忘而言，我们的方法的表现比当前的最新方法更好。与基于情节的内存和基于面具的方法相比，我们的方法还提供了更好的内存效率。我们的代码将在https://github.com/csiplab/task-increment-rank-update.git上找到。

当随着时间的推移学习任务时，人工神经网络遭受称为灾难性遗忘（CF）的问题。当在训练网络的训练过程中覆盖网络的权重，导致忘记旧信息的新任务时，会发生这种情况。为了解决这个问题，我们提出了META可重复使用的知识或标记，这是一种新的方法，可以在学习新任务时促进重量可重用性而不是覆盖。具体来说，标记在任务之间保留一组共享权重。我们将这些共享权重设定为共同的知识库（KB），不仅用于学习新任务，而且还富有以丰富的新知识，因为模型了解新任务。标记背后的关键组件是两倍。一方面，冶金学习方法提供了逐步丰富KB的关键机制，并在任务之间促进重量可重用性。另一方面，一组培训掩模提供了选择性地从KB相关权重中选择的关键机制来解决每个任务。通过使用Mark，我们实现了最普遍的基准，在几个流行的基准中实现了最新的基准，在20分拆性MiniimAgenet数据集上超过了平均精度的最佳性能方法，同时使用55％的数量来实现几乎零遗忘参数。此外，消融研究提供了证据，实际上，标记正在学习每个任务选择性地使用的可重复使用的知识。

We propose a novel deep network architecture for lifelong learning which we refer to as Dynamically Expandable Network (DEN), that can dynamically decide its network capacity as it trains on a sequence of tasks, to learn a compact overlapping knowledge sharing structure among tasks. DEN is efficiently trained in an online manner by performing selective retraining, dynamically expands network capacity upon arrival of each task with only the necessary number of units, and effectively prevents semantic drift by splitting/duplicating units and timestamping them. We validate DEN on multiple public datasets under lifelong learning scenarios, on which it not only significantly outperforms existing lifelong learning methods for deep networks, but also achieves the same level of performance as the batch counterparts with substantially fewer number of parameters. Further, the obtained network fine-tuned on all tasks obtained significantly better performance over the batch models, which shows that it can be used to estimate the optimal network structure even when all tasks are available in the first place.

Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly "intelligent" behavior. Here we apply recent techniques for explaining decisions of state-of-the-art learning machines and analyze various tasks from computer vision and arcade games. This showcases a spectrum of problem-solving behaviors ranging from naive and short-sighted, to wellinformed and strategic. We observe that standard performance evaluation metrics can be oblivious to distinguishing these diverse problem solving behaviors. Furthermore, we propose our semi-automated Spectral Relevance Analysis that provides a practically effective way of characterizing and validating the behavior of nonlinear learning machines. This helps to assess whether a learned model indeed delivers reliably for the problem that it was conceived for. Furthermore, our work intends to add a voice of caution to the ongoing excitement about machine intelligence and pledges to evaluate and judge some of these recent successes in a more nuanced manner.

当在具有不同分布的数据集上不断学习时，神经网络往往会忘记以前学习的知识，这一现象被称为灾难性遗忘。数据集之间的分配更改会导致更多的遗忘。最近，基于参数 - 隔离的方法在克服遗忘时具有巨大的潜力。但是，当他们在培训过程中修复每个数据集的神经路径时，他们的概括不佳，并且在推断过程中需要数据集标签。此外，他们不支持向后的知识转移，因为它们优先于过去的数据。在本文中，我们提出了一种名为ADAPTCL的新的自适应学习方法，该方法完全重复使用并在学习的参数上生长，以克服灾难性的遗忘，并允许在不需要数据集标签的情况下进行积极的向后传输。我们提出的技术通过允许最佳的冷冻参数重复使用在相同的神经路径上生长。此外，它使用参数级数据驱动的修剪来为数据分配同等优先级。我们对MNIST变体，域和食物新鲜度检测数据集进行了广泛的实验，而无需数据集标签。结果表明，我们所提出的方法优于替代基线，可以最大程度地减少遗忘和实现积极的向后知识转移。

Explainable AI transforms opaque decision strategies of ML models into explanations that are interpretable by the user, for example, identifying the contribution of each input feature to the prediction at hand. Such explanations, however, entangle the potentially multiple factors that enter into the overall complex decision strategy. We propose to disentangle explanations by finding relevant subspaces in activation space that can be mapped to more abstract human-understandable concepts and enable a joint attribution on concepts and input features. To automatically extract the desired representation, we propose new subspace analysis formulations that extend the principle of PCA and subspace analysis to explanations. These novel analyses, which we call principal relevant component analysis (PRCA) and disentangled relevant subspace analysis (DRSA), optimize relevance of projected activations rather than the more traditional variance or kurtosis. This enables a much stronger focus on subspaces that are truly relevant for the prediction and the explanation, in particular, ignoring activations or concepts to which the prediction model is invariant. Our approach is general enough to work alongside common attribution techniques such as Shapley Value, Integrated Gradients, or LRP. Our proposed methods show to be practically useful and compare favorably to the state of the art as demonstrated on benchmarks and three use cases.

Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is mediated by a rich set of neurocognitive mechanisms that together contribute to the development and specialization of our sensorimotor skills as well as to long-term memory consolidation and retrieval. Consequently, lifelong learning capabilities are crucial for computational systems and autonomous agents interacting in the real world and processing continuous streams of information. However, lifelong learning remains a long-standing challenge for machine learning and neural network models since the continual acquisition of incrementally available information from non-stationary data distributions generally leads to catastrophic forgetting or interference. This limitation represents a major drawback for state-of-the-art deep neural network models that typically learn representations from stationary batches of training data, thus without accounting for situations in which information becomes incrementally available over time. In this review, we critically summarize the main challenges linked to lifelong learning for artificial learning systems and compare existing neural network approaches that alleviate, to different extents, catastrophic forgetting. Although significant advances have been made in domain-specific learning with neural networks, extensive research efforts are required for the development of robust lifelong learning on autonomous agents and robots. We discuss well-established and emerging research motivated by lifelong learning factors in biological systems such as structural plasticity, memory replay, curriculum and transfer learning, intrinsic motivation, and multisensory integration.

人的大脑能够依次地学习任务，而无需忘记。但是，深度神经网络（DNN）在学习一项任务时遭受灾难性遗忘。我们考虑了一个挑战，考虑了一个课堂学习方案，在该方案中，DNN看到测试数据而不知道该数据启动的任务。在培训期间，持续的捕获和选择（CP＆S）在DNN中找到了负责解决给定任务的子网。然后，在推理期间，CP＆S选择正确的子网以对该任务进行预测。通过培训DNN的可用神经元连接（以前未经训练）来创建一个新的子网络，从而通过修剪来学习一项新任务，该连接可以包括以前训练的其他子网络（S），因为它没有更新共享的连接，因为它可以属于其他子网络（S）。这使得通过在DNN中创建专门的区域而不会相互冲突的同时仍允许知识转移在其中，可以消除灾难性的遗忘。 CP＆S策略采用不同的子网络选择策略实施，揭示了在各种数据集（CIFAR-100，CUB-200，2011年，Imagenet-100和Imagenet-100）上测试的最先进的持续学习方法的卓越性能。特别是，CP＆S能够从Imagenet-1000中依次学习10个任务，以确保94％的精度，而遗忘可忽略不计，这是课堂学习学习的首要结果。据作者所知，与最佳替代方法相比，这表示准确性高于20％的改善。

持续学习的目标（CL）是随着时间的推移学习不同的任务。与CL相关的主要Desiderata是在旧任务上保持绩效，利用后者来改善未来任务的学习，并在培训过程中引入最小的开销（例如，不需要增长的模型或再培训）。我们建议通过固定密度的稀疏神经网络来解决这些避难所的神经启发性塑性适应（NISPA）体系结构。 NISPA形成了稳定的途径，可以从较旧的任务中保存知识。此外，NISPA使用连接重新设计来创建新的塑料路径，以重用有关新任务的现有知识。我们对EMNIST，FashionMnist，CIFAR10和CIFAR100数据集的广泛评估表明，NISPA的表现明显胜过代表性的最先进的持续学习基线，并且与盆地相比，它的可学习参数最多少了十倍。我们还认为稀疏是持续学习的重要组成部分。 NISPA代码可在https://github.com/burakgurbuz97/nispa上获得。

在连续学习期间，人工神经网络（ANNS）经历灾难性的遗忘（CF）。相比之下，大脑可以在没有任何灾难性遗忘的迹象的情况下连续学习。尖峰神经网络（SNNS）是下一代ANN，具有从生物神经网络借入的许多功能。因此，SNNS可能希望更好地适应CF。在本文中，我们研究SNNS对CF的易感性，并测试几种用于减轻灾难性遗忘的生物启发方法。 SNNS受到基于Spike-Timing依赖的塑性（STDP）的生物合理的本地培训规则。本地培训禁止基于全局损失函数的梯度直接使用CF防御方法。我们开发并测试了该方法，以确定基于随机Langevin动态的突触（重量）的重要性，而无需梯度。还测试了一种从模拟神经网络改编的灾难性遗忘预防的其他几种方法。实验是在Spyketorch环境中自由的数据集进行的。

Humans can learn in a continuous manner. Old rarely utilized knowledge can be overwritten by new incoming information while important, frequently used knowledge is prevented from being erased. In artificial learning systems, lifelong learning so far has focused mainly on accumulating knowledge over tasks and overcoming catastrophic forgetting. In this paper, we argue that, given the limited model capacity and the unlimited new information to be learned, knowledge has to be preserved or erased selectively. Inspired by neuroplasticity, we propose a novel approach for lifelong learning, coined Memory Aware Synapses (MAS). It computes the importance of the parameters of a neural network in an unsupervised and online manner. Given a new sample which is fed to the network, MAS accumulates an importance measure for each parameter of the network, based on how sensitive the predicted output function is to a change in this parameter. When learning a new task, changes to important parameters can then be penalized, effectively preventing important knowledge related to previous tasks from being overwritten. Further, we show an interesting connection between a local version of our method and Hebb's rule, which is a model for the learning process in the brain. We test our method on a sequence of object recognition tasks and on the challenging problem of learning an embedding for predicting <subject, predicate, object> triplets. We show state-of-the-art performance and, for the first time, the ability to adapt the importance of the parameters based on unlabeled data towards what the network needs (not) to forget, which may vary depending on test conditions.

人类的持续学习（CL）能力与稳定性与可塑性困境密切相关，描述了人类如何实现持续的学习能力和保存的学习信息。自发育以来，CL的概念始终存在于人工智能（AI）中。本文提出了对CL的全面审查。与之前的评论不同，主要关注CL中的灾难性遗忘现象，本文根据稳定性与可塑性机制的宏观视角来调查CL。类似于生物对应物，“智能”AI代理商应该是I）记住以前学到的信息（信息回流）; ii）不断推断新信息（信息浏览:); iii）转移有用的信息（信息转移），以实现高级CL。根据分类学，评估度量，算法，应用以及一些打开问题。我们的主要贡献涉及I）从人工综合情报层面重新检查CL; ii）在CL主题提供详细和广泛的概述; iii）提出一些关于CL潜在发展的新颖思路。

Deep Neural Networks (DNNs) have demonstrated impressive performance in complex machine learning tasks such as image classification or speech recognition. However, due to their multi-layer nonlinear structure, they are not transparent, i.e., it is hard to grasp what makes them arrive at a particular classification or recognition decision given a new unseen data sample. Recently, several approaches have been proposed enabling one to understand and interpret the reasoning embodied in a DNN for a single test image. These methods quantify the "importance" of individual pixels wrt the classification decision and allow a visualization in terms of a heatmap in pixel/input space. While the usefulness of heatmaps can be judged subjectively by a human, an objective quality measure is missing. In this paper we present a general methodology based on region perturbation for evaluating ordered collections of pixels such as heatmaps. We compare heatmaps computed by three different methods on the SUN397, ILSVRC2012 and MIT Places data sets. Our main result is that the recently proposed Layer-wise Relevance Propagation (LRP) algorithm qualitatively and quantitatively provides a better explanation of what made a DNN arrive at a particular classification decision than the sensitivity-based approach or the deconvolution method. We provide theoretical arguments to explain this result and discuss its practical implications. Finally, we investigate the use of heatmaps for unsupervised assessment of neural network performance.