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.

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.

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。

恶意软件（恶意软件）分类为持续学习（CL）制度提供了独特的挑战，这是由于每天收到的新样本的数量以及恶意软件的发展以利用新漏洞。在典型的一天中，防病毒供应商将获得数十万个独特的软件，包括恶意和良性，并且在恶意软件分类器的一生中，有超过十亿个样品很容易积累。鉴于问题的规模，使用持续学习技术的顺序培训可以在减少培训和存储开销方面提供可观的好处。但是，迄今为止，还没有对CL应用于恶意软件分类任务的探索。在本文中，我们研究了11种应用于三个恶意软件任务的CL技术，涵盖了常见的增量学习方案，包括任务，类和域增量学习（IL）。具体而言，使用两个现实的大规模恶意软件数据集，我们评估了CL方法在二进制恶意软件分类（domain-il）和多类恶意软件家庭分类（Task-IL和类IL）任务上的性能。令我们惊讶的是，在几乎所有情况下，持续的学习方法显着不足以使训练数据的幼稚关节重播 - 在某些情况下，将精度降低了70个百分点以上。与关节重播相比，有选择性重播20％的存储数据的一种简单方法可以实现更好的性能，占训练时间的50％。最后，我们讨论了CL技术表现出乎意料差的潜在原因，希望它激发进一步研究在恶意软件分类域中更有效的技术。

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.

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.

人类智慧的主食是以不断的方式获取知识的能力。在Stark对比度下，深网络忘记灾难性，而且为此原因，类增量连续学习促进方法的子字段逐步学习一系列任务，将顺序获得的知识混合成综合预测。这项工作旨在评估和克服我们以前提案黑暗体验重播（Der）的陷阱，这是一种简单有效的方法，将排练和知识蒸馏结合在一起。灵感来自于我们的思想不断重写过去的回忆和对未来的期望，我们赋予了我的能力，即我的能力来修改其重播记忆，以欢迎有关过去数据II的新信息II）为学习尚未公开的课程铺平了道路。我们表明，这些策略的应用导致了显着的改进;实际上，得到的方法 - 被称为扩展-DAR（X-DER） - 优于标准基准（如CiFar-100和MiniimAgeNet）的技术状态，并且这里引入了一个新颖的。为了更好地了解，我们进一步提供了广泛的消融研究，以证实并扩展了我们以前研究的结果（例如，在持续学习设置中知识蒸馏和漂流最小值的价值）。

持续学习旨在快速，不断地从一系列任务中学习当前的任务。与其他类型的方法相比，基于经验重播的方法表现出了极大的优势来克服灾难性的遗忘。该方法的一个常见局限性是上一个任务和当前任务之间的数据不平衡，这将进一步加剧遗忘。此外，如何在这种情况下有效解决稳定性困境也是一个紧迫的问题。在本文中，我们通过提出一个通过多尺度知识蒸馏和数据扩展（MMKDDA）提出一个名为Meta学习更新的新框架来克服这些挑战。具体而言，我们应用多尺度知识蒸馏来掌握不同特征级别的远程和短期空间关系的演变，以减轻数据不平衡问题。此外，我们的方法在在线持续训练程序中混合了来自情节记忆和当前任务的样品，从而减轻了由于概率分布的变化而减轻了侧面影响。此外，我们通过元学习更新来优化我们的模型，该更新诉诸于前面所看到的任务数量，这有助于保持稳定性和可塑性之间的更好平衡。最后，我们对四个基准数据集的实验评估显示了提出的MMKDDA框架对其他流行基线的有效性，并且还进行了消融研究，以进一步分析每个组件在我们的框架中的作用。

Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off between transfer and interference that can be optimized by enforcing gradient alignment across examples. We then propose a new algorithm, Meta-Experience Replay (MER), that directly exploits this view by combining experience replay with optimization based meta-learning. This method learns parameters that make interference based on future gradients less likely and transfer based on future gradients more likely. 1 We conduct experiments across continual lifelong supervised learning benchmarks and non-stationary reinforcement learning environments demonstrating that our approach consistently outperforms recently proposed baselines for continual learning. Our experiments show that the gap between the performance of MER and baseline algorithms grows both as the environment gets more non-stationary and as the fraction of the total experiences stored gets smaller.

在基于人工神经网络的终身学习系统中，最大的障碍之一是在遇到新信息时无法保留旧知识。这种现象被称为灾难性遗忘。在本文中，我们提出了一种新型的连接主义架构，即顺序的神经编码网络，在从数据点流中学习时忘记了，并且与当今的网络不同，它不会通过流行的错误反向传播来学习。基于预测性处理的神经认知理论，我们的模型以生物学上可行的方式适应了突触，而另一个神经系统学会了指导和控制这种类似皮层的结构，模仿了一些基础神经节的某些任务连续控制功能。在我们的实验中，我们证明了与标准神经模型相比，我们的自组织系统经历的遗忘大大降低，表现优于先前提出的方法，包括基于排练/数据缓冲的方法，包括标准（SplitMnist，SplitMnist，Split Mnist等） 。）和定制基准测试，即使以溪流式的方式进行了训练。我们的工作提供了证据表明，在实际神经元系统中模仿机制，例如本地学习，横向竞争，可以产生新的方向和可能性，以应对终身机器学习的巨大挑战。

We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters and is designed to preserve performance on previously encountered tasks while accelerating learning progress on subsequent problems. This is achieved by training a network with two components: A knowledge base, capable of solving previously encountered problems, which is connected to an active column that is employed to efficiently learn the current task. After learning a new task, the active column is distilled into the knowledge base, taking care to protect any previously acquired skills. This cycle of active learning (progression) followed by consolidation (compression) requires no architecture growth, no access to or storing of previous data or tasks, and no task-specific parameters. We demonstrate the progress & compress approach on sequential classification of handwritten alphabets as well as two reinforcement learning domains: Atari games and 3D maze navigation.

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.

模块化是持续学习（CL）的令人信服的解决方案，是相关任务建模的问题。学习和组合模块来解决不同的任务提供了一种抽象来解决CL的主要挑战，包括灾难性的遗忘，向后和向前传输跨任务以及子线性模型的增长。我们引入本地模块组成（LMC），该方法是模块化CL的方法，其中每个模块都提供了局部结构组件，其估计模块与输入的相关性。基于本地相关评分进行动态模块组合。我们展示了对任务身份（IDS）的不可知性来自（本地）结构学习，该结构学习是特定于模块和/或模型特定于以前的作品，使LMC适用于与以前的作品相比的更多CL设置。此外，LMC还跟踪输入分布的统计信息，并在检测到异常样本时添加新模块。在第一组实验中，LMC与最近的持续转移学习基准上的现有方法相比，不需要任务标识。在另一个研究中，我们表明结构学习的局部性允许LMC插入相关但未遵守的任务（OOD），以及在不同任务序列上独立于不同的任务序列培训的模块化网络，而无需任何微调。最后，在寻找LMC的限制，我们在30和100个任务的更具挑战性序列上研究它，展示了本地模块选择在存在大量候选模块时变得更具挑战性。在此设置中，与Oracle基准的基线相比，最佳执行LMC产生的模块更少，但它达到了较低的总体精度。 CodeBase可在https://github.com/oleksost/lmc下找到。

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。

尽管人工神经网络（ANN）取得了重大进展，但其设计过程仍在臭名昭著，这主要取决于直觉，经验和反复试验。这个依赖人类的过程通常很耗时，容易出现错误。此外，这些模型通常与其训练环境绑定，而没有考虑其周围环境的变化。神经网络的持续适应性和自动化对于部署后模型可访问性的几个领域至关重要（例如，IoT设备，自动驾驶汽车等）。此外，即使是可访问的模型，也需要频繁的维护后部署后，以克服诸如概念/数据漂移之类的问题，这可能是繁琐且限制性的。当前关于自适应ANN的艺术状况仍然是研究的过早领域。然而，一种自动化和持续学习形式的神经体系结构搜索（NAS）最近在深度学习研究领域中获得了越来越多的动力，旨在提供更强大和适应性的ANN开发框架。这项研究是关于汽车和CL之间交集的首次广泛综述，概述了可以促进ANN中充分自动化和终身可塑性的不同方法的研究方向。

深度神经网络的强大学习能力使强化学习者能够直接从连续环境中学习有效的控制政策。从理论上讲，为了实现稳定的性能，神经网络假设I.I.D.不幸的是，在训练数据在时间上相关且非平稳的一般强化学习范式中，输入不存在。这个问题可能导致“灾难性干扰”和性能崩溃的现象。在本文中，我们提出智商，即干涉意识深度Q学习，以减轻单任务深度加固学习中的灾难性干扰。具体来说，我们求助于在线聚类，以实现在线上下文部门，以及一个多头网络和一个知识蒸馏正规化术语，用于保留学习上下文的政策。与现有方法相比，智商基于深Q网络，始终如一地提高稳定性和性能，并通过对经典控制和ATARI任务进行了广泛的实验。该代码可在以下网址公开获取：https：//github.com/sweety-dm/interference-aware-ware-deep-q-learning。

Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle this challenge and propose an approach for continual semi-supervised learning -- a setting where not all the data samples are labeled. An underlying issue in this scenario is the model forgetting representations of unlabeled data and overfitting the labeled ones. We leverage the power of nearest-neighbor classifiers to non-linearly partition the feature space and learn a strong representation for the current task, as well as distill relevant information from previous tasks. We perform a thorough experimental evaluation and show that our method outperforms all the existing approaches by large margins, setting a strong state of the art on the continual semi-supervised learning paradigm. For example, on CIFAR100 we surpass several others even when using at least 30 times less supervision (0.8% vs. 25% of annotations).

根据互补学习系统（CLS）理论〜\ cite {mcclelland1995there}在神经科学中，人类通过两个补充系统有效\ emph {持续学习}：一种快速学习系统，以海马为中心，用于海马，以快速学习细节，个人体验，个人体验，个人体验，个人体验，个人体验，个人体验，个人体验，个人体验的快速学习， ;以及位于新皮层中的缓慢学习系统，以逐步获取有关环境的结构化知识。在该理论的激励下，我们提出\ emph {dualnets}（对于双网络），这是一个一般的持续学习框架，该框架包括一个快速学习系统，用于监督从特定任务和慢速学习系统中的模式分离代表学习，用于表示任务的慢学习系统 - 不可知论的一般代表通过自我监督学习（SSL）。双网符可以无缝地将两种表示类型纳入整体框架中，以促进在深层神经网络中更好地持续学习。通过广泛的实验，我们在各种持续的学习协议上展示了双网络的有希望的结果，从标准离线，任务感知设置到具有挑战性的在线，无任务的场景。值得注意的是，在Ctrl〜 \ Cite {veniat2020202020202020202020202020202020202020202020202020202020202021- coite {ostapenko2021-continual}的基准中。此外，我们进行了全面的消融研究，以验证双nets功效，鲁棒性和可伸缩性。代码可在\ url {https://github.com/phquang/dualnet}上公开获得。

The ability to dynamically adapt neural networks to newly-available data without performance deterioration would revolutionize deep learning applications. Streaming learning (i.e., learning from one data example at a time) has the potential to enable such real-time adaptation, but current approaches i) freeze a majority of network parameters during streaming and ii) are dependent upon offline, base initialization procedures over large subsets of data, which damages performance and limits applicability. To mitigate these shortcomings, we propose Cold Start Streaming Learning (CSSL), a simple, end-to-end approach for streaming learning with deep networks that uses a combination of replay and data augmentation to avoid catastrophic forgetting. Because CSSL updates all model parameters during streaming, the algorithm is capable of beginning streaming from a random initialization, making base initialization optional. Going further, the algorithm's simplicity allows theoretical convergence guarantees to be derived using analysis of the Neural Tangent Random Feature (NTRF). In experiments, we find that CSSL outperforms existing baselines for streaming learning in experiments on CIFAR100, ImageNet, and Core50 datasets. Additionally, we propose a novel multi-task streaming learning setting and show that CSSL performs favorably in this domain. Put simply, CSSL performs well and demonstrates that the complicated, multi-step training pipelines adopted by most streaming methodologies can be replaced with a simple, end-to-end learning approach without sacrificing performance.

现代ML方法在培训数据是IID，大规模和良好标记的时候Excel。在不太理想的条件下学习仍然是一个开放的挑战。在不利条件下，几次射击，持续的，转移和代表学习的子场在学习中取得了很大的进步;通过方法和见解，每个都提供了独特的优势。这些方法解决了不同的挑战，例如依次到达的数据或稀缺的训练示例，然而，在部署之前，ML系统将面临困难的条件。因此，需要可以处理实际设置中许多学习挑战的一般ML系统。为了促进一般ML方法目标的研究，我们介绍了一个新的统一评估框架 - 流体（灵活的顺序数据）。流体集成了几次拍摄，持续的，转移和表示学习的目标，同时能够比较和整合这些子场的技术。在流体中，学习者面临数据流，并且必须在选择如何更新自身时进行顺序预测，快速调整到新颖的类别，并处理更改的数据分布;虽然会计计算总额。我们对广泛的方法进行实验，这些方法阐述了新的洞察当前解决方案的优缺点并表明解决了新的研究问题。作为更一般方法的起点，我们展示了两种新的基线，其在流体上优于其他评估的方法。项目页面：https：//raivn.cs.washington.edu/projects/fluid/。