The color has been normalized to be between 0 and 1 which does not affect the clustering or visualization. We can see that output representation from later layers yield more patterned kernel matrices with more erratic clustering.

While the deployment of deep learning models on edge devices is increasing, these models often lack robustness when faced with dynamic changes in sensed data. This can be attributed to sensor drift, or variations in the data compared to what was used during offline training due to factors such as specific sensor placement or naturally changing sensing conditions. Hence, achieving the desired robustness necessitates the utilization of either an invariant architecture or specialized training approaches, like data augmentation. Alternatively, input transformations can be treated as a domain shift problem, and solved by post-deployment model adaptation. In this paper, we train a parameterized subspace of configurable networks, where an optimal network for a particular parameter setting is part of this subspace. The obtained subspace is low-dimensional and has a surprisingly simple structure even for complex, non-invertible transformations of the input, leading to an exceptionally high efficiency of subspace-configurable networks (SCNs) when limited storage and computing resources are at stake. We evaluate SCNs on a wide range of standard datasets, architectures, and transformations, and demonstrate their power on resource-constrained IoT devices, where they can take up to 2.4 times less RAM and be 7.6 times faster at inference time than a model that achieves the same test set accuracy, yet is trained with data augmentations to cover the desired range of input transformations.

Most solutions to the inventory management problem assume a centralization of information that is incompatible with organisational constraints in real supply chain networks. The inventory management problem is a well-known planning problem in operations research, concerned with finding the optimal re-order policy for nodes in a supply chain. While many centralized solutions to the problem exist, they are not applicable to real-world supply chains made up of independent entities. The problem can however be naturally decomposed into sub-problems, each associated with an independent entity, turning it into a multi-agent system. Therefore, a decentralized data-driven solution to inventory management problems using multi-agent reinforcement learning is proposed where each entity is controlled by an agent. Three multi-agent variations of the proximal policy optimization algorithm are investigated through simulations of different supply chain networks and levels of uncertainty. The centralized training decentralized execution framework is deployed, which relies on offline centralization during simulation-based policy identification, but enables decentralization when the policies are deployed online to the real system. Results show that using multi-agent proximal policy optimization with a centralized critic leads to performance very close to that of a centralized data-driven solution and outperforms a distributed model-based solution in most cases while respecting the information constraints of the system.

Existing object pose estimation methods commonly require a one-to-one point matching step that forces them to be separated into two consecutive stages: visual correspondence detection (e.g., by matching feature descriptors as part of a perception front-end) followed by geometric alignment (e.g., by optimizing a robust estimation objective for pointcloud registration or perspective-n-point). Instead, we propose a matching-free probabilistic formulation with two main benefits: i) it enables unified and concurrent optimization of both visual correspondence and geometric alignment, and ii) it can represent different plausible modes of the entire distribution of likely poses. This in turn allows for a more graceful treatment of geometric perception scenarios where establishing one-to-one matches between points is conceptually ill-defined, such as textureless, symmetrical and/or occluded objects and scenes where the correct pose is uncertain or there are multiple equally valid solutions.

The goal of this paper is to introduce pooling strategies for simplicial convolutional neural networks. Inspired by graph pooling methods, we introduce a general formulation for a simplicial pooling layer that performs: i) local aggregation of simplicial signals; ii) principled selection of sampling sets; iii) downsampling and simplicial topology adaptation. The general layer is then customized to design four different pooling strategies (i.e., max, top-k, self-attention, and separated top-k) grounded in the theory of topological signal processing. Also, we leverage the proposed layers in a hierarchical architecture that reduce complexity while representing data at different resolutions. Numerical results on real data benchmarks (i.e., flow and graph classification) illustrate the advantage of the proposed methods with respect to the state of the art.

This study focuses on simultaneous decision making for stochastic multi-echelon inventory optimization problems. Mixed supply chain networks are considered that may contain assembly or distribution nodes, or both, and may use nonlinear cost structure. We present a framework which uses deep neural networks as agents responsible for finding order-up-to levels for any desired components of the general supply chain network. Agents simultaneously interact with the environment in an unsupervised manner to minimize total inventory cost. Not only does this study consider several decision-makers simultaneously for stages of a general supply chain network, but it also presents clear and interpretable order-up-to levels. First, we numerically show the effectiveness of the method by solving newsvendor and serial supply chain networks and compare the results with the available closed form solutions for these settings. Then, we investigate a mixed supply chain network and a more general case study. The findings indicate that the proposed method performs better in terms of objective function values and the number of interactions with the environment compared to alternatives. In addition, the method finds inventory policies similar to simple base-stock policies for general SCNs. Moreover, we generally notice that for echelons closer to the source, fixed optimal order-up-to levels can be considerably larger than the expected demands these echelons observe.

"The funny thing about life is that it's temporary; that is to say, temporary in the'temporal' sense of the word, meaning that all living things and all that we do are subject to the precepts and effects of time." Many organisms perform best at certain hours of the day. The slug species Arion subfuscus, living in almost total darkness, knowing nothing about the Gregorian calendar, lays its eggs between the last week of August and the first week of September.1 Bees forage for nectar, knowing the best times to visit the best fields and the exact timing of nectar secretions for individual species of flowers. In the mid-20th century, the Austrian Nobel laureate Karl von Frisch provided enormous insights on honeybee communication and foraging time. He discovered that bees have internal clocks that tell them not only where the nectar is to be found but also precisely when that food will be ready. "I know of no other living creature," he wrote in his book on bee language, "that learns so easily as the bee when, according to its'internal clock,' to come to the table."2 Even without a light clue, the plants were able to tell time.

-- Despite the superiority of convolutional neural networks demonstrated in time series modeling and forecasting, it has not been fully explored on the design of the neural network architecture as well as the tuning of the hyper-parameters. Inspired by the iterative construction strategy for building a random multilayer perceptron, we propose a novel Error-feedback Stochastic Configuration (ESC) strategy to construct a random Convolutional Neural Network (ESC-CNN) for time series forecasting task, which builds the network architecture adaptively. The ESC strategy suggests that random filters and neurons of the error-feedback fully connected layer are incre-mentally added in a manner that they can steadily compensate the prediction error during the construction process, and a filter selection strategy is introduced to secure that ESC-CNN holds the universal approximation property, providing helpful information at each iterative process for the prediction. The performance of ESC-CNN is justified on its prediction accuracy for one-step- ahead and multi-step-ahead forecasting tasks. Comprehensive experiments on a synthetic dataset and two real-world datasets show that the proposed ESC-CNN not only outperforms the state-of-art random neural networks, but also exhibits strong predictive power in comparison to trained Convolution Neural Networks and Long Short-T erm Memory models, demonstrating the effectiveness of ESC-CNN in time series forecasting. Time series forecasting, especially computational intelligence enabled time series forecasting, is of great importance for a learning system in dynamic environments, and plays a vital role in applications such as in finance [1]-[3], energy [4]- [6], traffic [7]-[9], and electric load [10]-[12], etc. Recently, convolutional neural networks (CNNs) have been successfully implemented for time series forecasting tasks, benefiting from its strength in extracting local features via multiple convolu-tional filters and learning representation by fully connected layers [13]-[16].

Citizen science projects are successful at gathering rich datasets for various applications. However, the data collected by citizen scientists are often biased --- in particular, aligned more with the citizens' preferences than with scientific objectives. We propose the Shift Compensation Network (SCN), an end-to-end learning scheme which learns the shift from the scientific objectives to the biased data while compensating for the shift by re-weighting the training data. Applied to bird observational data from the citizen science project eBird, we demonstrate how SCN quantifies the data distribution shift and outperforms supervised learning models that do not address the data bias. Compared with competing models in the context of covariate shift, we further demonstrate the advantage of SCN in both its effectiveness and its capability of handling massive high-dimensional data.