Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOne neuron is more informative than a deep neural network for aftershock pattern forecasting
56
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
29 August 2018: Artificial intelligence nails predictions of earthquake aftershocks. This Nature News headline is based on the results of DeVries et al. (2018) who forecasted the spatial distribution of aftershocks using Deep Learning (DL) and static stress feature engineering. Using receiver operating characteristic (ROC) curves and the area under the curve (AUC) metric, the authors found that a deep neural network (DNN) yields AUC = 0.85 compared to AUC = 0.58 for classical Coulomb stress. They further showed that this result was physically interpretable, with various stress metrics (e.g. sum of absolute stress components, maximum shear stress, von Mises yield criterion) explaining most of the DNN result. We here clarify that AUC c. 0.85 had already been obtained using ROC curves for the same scalar metrics and by the same authors in 2017. This suggests that DL - in fact - does not improve prediction compared to simpler baseline models. We reformulate the 2017 results in probabilistic terms using logistic regression (i.e., one neural network node) and obtain AUC = 0.85 using 2 free parameters versus the 13,451 parameters used by DeVries et al. (2018). We further show that measured distance and mainshock average slip can be used instead of stress, yielding an improved AUC = 0.86, again with a simple logistic regression. This demonstrates that the proposed DNN so far does not provide any new insight (predictive or inferential) in this domain.
rate research
Read More
The Capsule Network is widely believed to be more robust than Convolutional Networks. However, there are no comprehensive comparisons between these two networks, and it is also unknown which components in the CapsNet affect its robustness. In this paper, we first carefully examine the special designs in CapsNet that differ from that of a ConvNet commonly used for image classification. The examination reveals five major new/different components in CapsNet: a transformation process, a dynamic routing layer, a squashing function, a marginal loss other than cross-entropy loss, and an additional class-conditional reconstruction loss for regularization. Along with these major differences, we conduct comprehensive ablation studies on three kinds of robustness, including affine transformation, overlapping digits, and semantic representation. The study reveals that some designs, which are thought critical to CapsNet, actually can harm its robustness, i.e., the dynamic routing layer and the transformation process, while others are beneficial for the robustness. Based on these findings, we propose enhanced ConvNets simply by introducing the essential components behind the CapsNets success. The proposed simple ConvNets can achieve better robustness than the CapsNet.
Entanglement has long stood as one of the characteristic features of quantum mechanics, yet recent developments have emphasized the importance of quantumness beyond entanglement for quantum foundations and technologies. We demonstrate that entanglement cannot entirely capture the worst-case sensitivity in quantum interferometry, when quantum probes are used to estimate the phase imprinted by a Hamiltonian, with fixed energy levels but variable eigenbasis, acting on one arm of an interferometer. This is shown by defining a bipartite entanglement monotone tailored to this interferometric setting and proving that it never exceeds the so-called interferometric power, a quantity which relies on more general quantum correlations beyond entanglement and captures the relevant resource. We then prove that the interferometric power can never increase when local commutativity-preserving operations are applied to qubit probes, an important step to validate such a quantity as a genuine quantum correlations monotone. These findings are accompanied by a room-temperature nuclear magnetic resonance experimental investigation, in which two-qubit states with extremal (maximal and minimal) interferometric power at fixed entanglement are produced and characterized.
Visual patterns represent the discernible regularity in the visual world. They capture the essential nature of visual objects or scenes. Understanding and modeling visual patterns is a fundamental problem in visual recognition that has wide ranging applications. In this paper, we study the problem of visual pattern mining and propose a novel deep neural network architecture called PatternNet for discovering these patterns that are both discriminative and representative. The proposed PatternNet leverages the filters in the last convolution layer of a convolutional neural network to find locally consistent visual patches, and by combining these filters we can effectively discover unique visual patterns. In addition, PatternNet can discover visual patterns efficiently without performing expensive image patch sampling, and this advantage provides an order of magnitude speedup compared to most other approaches. We evaluate the proposed PatternNet subjectively by showing randomly selected visual patterns which are discovered by our method and quantitatively by performing image classification with the identified visual patterns and comparing our performance with the current state-of-the-art. We also directly evaluate the quality of the discovered visual patterns by leveraging the identified patterns as proposed objects in an image and compare with other relevant methods. Our proposed network and procedure, PatterNet, is able to outperform competing methods for the tasks described.
An evolution strategy (ES) variant based on a simplification of a natural evolution strategy recently attracted attention because it performs surprisingly well in challenging deep reinforcement learning domains. It searches for neural network parameters by generating perturbations to the current set of parameters, checking their performance, and moving in the aggregate direction of higher reward. Because it resembles a traditional finite-difference approximation of the reward gradient, it can naturally be confused with one. However, this ES optimizes for a different gradient than just reward: It optimizes for the average reward of the entire population, thereby seeking parameters that are robust to perturbation. This difference can channel ES into distinct areas of the search space relative to gradient descent, and also consequently to networks with distinct properties. This unique robustness-seeking property, and its consequences for optimization, are demonstrated in several domains. They include humanoid locomotion, where networks from policy gradient-based reinforcement learning are significantly less robust to parameter perturbation than ES-based policies solving the same task. While the implications of such robustness and robustness-seeking remain open to further study, this works main contribution is to highlight such differences and their potential importance.
Physical processes thatobtain, process, and erase information involve tradeoffs between information and energy. The fundamental energetic value of a bit of information exchanged with a reservoir at temperature T is kT ln2. This paper investigates the situation in which information is missing about just what physical process is about to take place. The fundamental energetic value of such information can be far greater than kT ln2 per bit.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
