Related papers: The central error of M. W. Evans ECE theory - a ty…
Grammatical Error Correction (GEC) should not focus only on high accuracy of corrections but also on interpretability for language learning. However, existing neural-based GEC models mainly aim at improving accuracy, and their…
In various chemical systems enthalpy-entropy compensation (EEC) is a well-known rule of behavior, although the physical roots of it are still not completely understood. It has been frequently questioned whether EEC is a truly physical…
Counterfactual explanations (CEs) are a practical tool for demonstrating why machine learning classifiers make particular decisions. For CEs to be useful, it is important that they are easy for users to interpret. Existing methods for…
Counterfactual explanations (CEs) offer a human-understandable way to explain decisions by identifying specific changes to the input parameters of a base or present model that would lead to a desired change in the outcome. For optimization…
Unfortunately, the article "A Comparative Study to Benchmark Cross-project Defect Prediction Approaches" has a problem in the statistical analysis which was pointed out almost immediately after the pre-print of the article appeared online.…
I have noted a number of errors, most of them quite minor, in the {\em Encyclopedia of Cosmology} (New York and London: Garland), 1993, Norriss S. Hetherington, ed. The majority occur in my mathematically verbose article, ``Fundamental…
In this paper we present a heuristic method to provide individual explanations for those elements in a dataset (data points) which are wrongly predicted by a given classifier. Since the general case is too difficult, in the present work we…
While the expected calibration error (ECE), which employs binning, is widely adopted to evaluate the calibration performance of machine learning models, theoretical understanding of its estimation bias is limited. In this paper, we present…
Manuscript astro-ph/0504486 is a clear example of the fundamental conceptual flaw that had persisted for the past 100 years. Namely, the failure to realize that mass-energy equivalence, as applied to a propagating light particle (photon),…
The repeated community-wide reuse of test sets in popular benchmark problems raises doubts about the credibility of reported test-error rates. Verifying whether a learned model is overfitted to a test set is challenging as independent test…
It is well known that mean-field theories fail to reproduce the experimentally known critical exponents. The traditional argument which explain this failure of mean-field theories near a critical point is the Ginsburg criterion in which…
This paper has been withdrawn by the author because there are some typos in proofs.
The paper entitled ``Against Many-Worlds Interpretations'' by A. Kent, which has recently been submitted to the e-Print archive (gr-qc/9703089) contained some misconceptions. The claims on Everett's many-worlds interpretation are quoted and…
Loss functions play a central role in supervised classification. Cross-entropy (CE) is widely used, whereas the mean absolute error (MAE) loss can offer robustness but is difficult to optimize. Interpolating between the CE and MAE losses,…
A form of generalisation error known as Off Training Set (OTS) error was recently introduced in [Wolpert, 1996b], along with a theorem showing that small training set error does not guarantee small OTS error, unless assumptions are made…
This article discusses several erroneous claims which appear in textbooks on numerical methods and computational physics. These are not typos or mistakes an individual author has made, but widespread misconceptions. In an attempt to stop…
Data-sparse settings such as robotic manipulation, molecular physics, and galaxy morphology classification are some of the hardest domains for deep learning. For these problems, equivariant networks can help improve modeling across…
We address the issue of the fallacy of the gauge concept in electromagnetism. The role of groupthink in the perpetuation of this concept in the physics literature is also discussed. Brief, elementary arguments suffice to demonstrate the…
There is a gap in Theorem 2.2 of the paper of Du (\cite{D_2010}). In this paper, we shall state the gap and repair it.
This article corrects two mistakes in the article "Coarse homology theories" [math.AT/0106183].