设计廉价的近似替代模型，该模型捕获昂贵的高保真行为的显着特征是设计优化的一种普遍方法。最近，深度学习（DL）模型被用作有前途的工程问题替代计算模型。但是，创建基于DL的替代物的主要挑战是模拟/标记大量的设计点，这对于计算昂贵和/或高维工程问题来说是耗时的。在目前的工作中，我们通过将主动学习（AL）方法与DL相结合，提出了一种新颖的抽样技术。我们称此方法为$ \ epsilon $ - 加权混合查询策略（$ \ epsilon $ -HQS），该策略的重点是对每次学习迭代的替代物的评估，并提供了设计空间中代理的失败概率的估计。通过重复使用已经收集的培训和测试数据，学习的故障概率将下一个迭代的抽样过程引向了高失败概率的区域。在经验评估期间，与其他样品选择方法相比，观察到替代物的精度更好。我们在两个不同的工程设计域，基于有限元的静态应力分析（计算昂贵的过程）和第二次海底螺旋桨设计（高维问题）中对此方法进行了经验评估。 https://github.com/vardhah/epsilon_weighted_hybrid_query_strategy

大多数基于机器学习的回归器从过去的观察结果有限的观察结果中提取信息，以便将来做出预测。因此，当对这些训练的模型的输入是具有与用于培训的数据明显不同的数据时，无法保证准确的预测。因此，使用这些模型在分布外输入数据上可能会导致与所需的结果完全不同的预测结果，这不仅是错误的，而且在某些情况下也可能是危险的。这些机器学习模型在任何系统中的成功部署都需要一个检测系统，该系统应该能够区分分布和分配数据（即与培训数据相似）。在本文中，我们使用降低的鲁棒随机切割森林（RRRCF）数据结构引入了一种新的检测过程方法，该方法可用于小型和大数据集。与强大的随机切割森林（RRCF）相似，RRRCF是一个结构化的，但训练数据子空间的表示形式减少了。该方法对低维数据和高维数据的经验结果表明，有关数据的推断可以有效地进行/退出训练分布，并且该模型很容易训练，而无需不困难的高参数调整。本文讨论了两个不同的用例，用于测试和验证结果。

机器学习模型在许多现实世界中都有普遍的应用，这增加了这些训练有素模型的行为中正确性的重要性。找到一个良好的测试用例，可以揭示这些训练有素的系统中的潜在失败可以帮助重新训练这些模型以提高其正确性。对于训练有素的模型，失败的发生很少。因此，由于较大的搜索空间，有限的计算资源和可用时间，通过评估输入搜索空间或随机搜索中的每个样本来搜索这些罕见情况将是昂贵的，有时是棘手的。在本文中，我们试图解决与传统随机搜索更快地发现这些故障方案的挑战。我们方法的核心思想是根据培训数据的观察，实际统计数据绘制的数据以及来自域专家的知识，将输入数据空间分离出高失败概率和低/最小故障概率区域的输入数据空间。 。使用这些信息，我们可以设计一个生成模型，从中我们可以生成具有很可能揭示潜在故障的场景。我们在两种不同的实验场景上评估了这种方法，并能够比传统的随机搜索快速发现此类故障一千倍。

在自动水下车辆（AUV）的设计过程中，压力容器具有关键作用。压力容器中包含干电子，电源和其他无法淹没的传感器。压力容器设计的传统设计方法涉及基于多个有限元分析（FEA）模拟并优化设计以找到满足需求的最佳设计。对于任何优化过程，运行这些夫妇在计算上都是非常昂贵的，而且很难进行数百个评估。在这种情况下，更好的方法是替代设计，目的是用一些基于学习的回归剂代替基于FEA的预测。一旦对一类问题进行了替代训练，就可以使用学习的响应表面来分析应力效应，而无需为该类别的问题运行FEA。为一类问题创建替代的挑战是数据生成。由于该过程的计算成本高昂，因此不可能密集采样设计空间，并且稀疏数据集上的学习响应表面变得困难。在实验过程中，我们观察到，基于深度学习的替代物在此类稀疏数据上优于其他回归模型。在目前的工作中，我们正在利用基于深度学习的模型来替换昂贵的有限元分析模拟过程。通过创建代理，我们可以比直接有限元分析更快地提高其他设计的预测。我们还将基于DL的替代物与基于其他经典机器学习（ML）回归模型（随机森林和梯度增强回归器）进行了比较。我们在稀疏数据上观察到，基于DL的替代物的性能要比其他回归模型好得多。

从自然语言嵌入中汲取灵感，我们提出了Astromer，这是一种基于变压器的模型，以创建光曲线的表示。Astromer接受了数以百万计的Macho R波段样品的培训，并且很容易对其进行微调以匹配与下游任务相关的特定域。例如，本文显示了使用预训练的表示形式对变量恒星进行分类的好处。此外，我们还提供了一个Python库，其中包括这项工作中使用的所有功能。我们的图书馆包括预先培训的模型，可用于增强深度学习模型的性能，减少计算资源，同时获得最新的结果。

Landing an unmanned aerial vehicle unmanned aerial vehicle (UAV) on top of an unmanned surface vehicle (USV) in harsh open waters is a challenging problem, owing to forces that can damage the UAV due to a severe roll and/or pitch angle of the USV during touchdown. To tackle this, we propose a novel model predictive control (MPC) approach enabling a UAV to land autonomously on a USV in these harsh conditions. The MPC employs a novel objective function and an online decomposition of the oscillatory motion of the vessel to predict, attempt, and accomplish the landing during near-zero tilt of the landing platform. The nonlinear prediction of the motion of the vessel is performed using visual data from an onboard camera. Therefore, the system does not require any communication with the USV or a control station. The proposed method was analyzed in numerous robotics simulations in harsh and extreme conditions and further validated in various real-world scenarios.

Real-world datasets exhibit imbalances of varying types and degrees. Several techniques based on re-weighting and margin adjustment of loss are often used to enhance the performance of neural networks, particularly on minority classes. In this work, we analyze the class-imbalanced learning problem by examining the loss landscape of neural networks trained with re-weighting and margin-based techniques. Specifically, we examine the spectral density of Hessian of class-wise loss, through which we observe that the network weights converge to a saddle point in the loss landscapes of minority classes. Following this observation, we also find that optimization methods designed to escape from saddle points can be effectively used to improve generalization on minority classes. We further theoretically and empirically demonstrate that Sharpness-Aware Minimization (SAM), a recent technique that encourages convergence to a flat minima, can be effectively used to escape saddle points for minority classes. Using SAM results in a 6.2\% increase in accuracy on the minority classes over the state-of-the-art Vector Scaling Loss, leading to an overall average increase of 4\% across imbalanced datasets. The code is available at: https://github.com/val-iisc/Saddle-LongTail.

Parkinson's disease is marked by altered and increased firing characteristics of pathological oscillations in the brain. In other words, it causes abnormal synchronous oscillations and suppression during neurological processing. In order to examine and regulate the synchronization and pathological oscillations in motor circuits, deep brain stimulators (DBS) are used. Although machine learning methods have been applied for the investigation of suppression, these models require large amounts of training data and computational power, both of which pose challenges to resource-constrained DBS. This research proposes a novel reinforcement learning (RL) framework for suppressing the synchronization in neuronal activity during episodes of neurological disorders with less power consumption. The proposed RL algorithm comprises an ensemble of a temporal representation of stimuli and a twin-delayed deep deterministic (TD3) policy gradient algorithm. We quantify the stability of the proposed framework to noise and reduced synchrony using RL for three pathological signaling regimes: regular, chaotic, and bursting, and further eliminate the undesirable oscillations. Furthermore, metrics such as evaluation rewards, energy supplied to the ensemble, and the mean point of convergence were used and compared to other RL algorithms, specifically the Advantage actor critic (A2C), the Actor critic with Kronecker-featured trust region (ACKTR), and the Proximal policy optimization (PPO).

Problem statement: Standardisation of AI fairness rules and benchmarks is challenging because AI fairness and other ethical requirements depend on multiple factors such as context, use case, type of the AI system, and so on. In this paper, we elaborate that the AI system is prone to biases at every stage of its lifecycle, from inception to its usage, and that all stages require due attention for mitigating AI bias. We need a standardised approach to handle AI fairness at every stage. Gap analysis: While AI fairness is a hot research topic, a holistic strategy for AI fairness is generally missing. Most researchers focus only on a few facets of AI model-building. Peer review shows excessive focus on biases in the datasets, fairness metrics, and algorithmic bias. In the process, other aspects affecting AI fairness get ignored. The solution proposed: We propose a comprehensive approach in the form of a novel seven-layer model, inspired by the Open System Interconnection (OSI) model, to standardise AI fairness handling. Despite the differences in the various aspects, most AI systems have similar model-building stages. The proposed model splits the AI system lifecycle into seven abstraction layers, each corresponding to a well-defined AI model-building or usage stage. We also provide checklists for each layer and deliberate on potential sources of bias in each layer and their mitigation methodologies. This work will facilitate layer-wise standardisation of AI fairness rules and benchmarking parameters.

We introduce a language generation task grounded in a popular video game environment. KNUDGE (KNowledge Constrained User-NPC Dialogue GEneration) involves generating dialogue trees conditioned on an ontology captured in natural language passages providing quest and entity specifications. KNUDGE is constructed from side quest dialogues drawn directly from game data of Obsidian Entertainment's The Outer Worlds, leading to real-world complexities in generation: (1) dialogues are branching trees as opposed to linear chains of utterances; (2) utterances must remain faithful to the game lore--character personas, backstories, and entity relationships; and (3) a dialogue must accurately reveal new quest-related details to the human player. We report results for supervised and in-context learning techniques, finding there is significant room for future work on creating realistic game-quality dialogues.