Related papers: Measuring the Feasibility of Analogical Transfer u…
Humans flexibly construct internal models to navigate novel situations. To be useful, these internal models must be sufficiently faithful to the environment that resource-limited planning leads to adequate outcomes; equally, they must be…
Multi-source transfer learning has been proven effective when within-target labeled data is scarce. Previous work focuses primarily on exploiting domain similarities and assumes that source domains are richly or at least comparably labeled.…
Analogy-making is at the core of human and artificial intelligence and creativity with applications to such diverse tasks as proving mathematical theorems and building mathematical theories, common sense reasoning, learning, language…
Analogical reasoning is effective in capturing linguistic regularities. This paper proposes an analogical reasoning task on Chinese. After delving into Chinese lexical knowledge, we sketch 68 implicit morphological relations and 28 explicit…
Adversarial attack transferability is well-recognized in deep learning. Prior work has partially explained transferability by recognizing common adversarial subspaces and correlations between decision boundaries, but little is known beyond…
A prevailing belief in attack and defense community is that the higher flatness of adversarial examples enables their better cross-model transferability, leading to a growing interest in employing sharpness-aware minimization and its…
In this paper, we investigate the principle that `good explanations are hard to vary' in the context of deep learning. We show that averaging gradients across examples -- akin to a logical OR of patterns -- can favor memorization and…
Adversarial examples for neural network image classifiers are known to be transferable: examples optimized to be misclassified by a source classifier are often misclassified as well by classifiers with different architectures. However,…
We study the relative complexity of equivalence relations and preorders from computability theory and complexity theory. Given binary relations $R, S$, a componentwise reducibility is defined by $ R\le S \iff \ex f \, \forall x, y \, [xRy…
The transferability of adversarial examples allows for the attack on unknown deep neural networks (DNNs), posing a serious threat to many applications and attracting great attention. In this paper, we improve the transferability of…
For each clone C on a set A there is an associated equivalence relation analogous to Green's R-relation, which relates two operations on A iff each one is a substitution instance of the other using operations from C. We study the clones for…
In order to behave intelligently both humans and machines have to represent their knowledge adequately for how it is used. Humans often use analogies to transfer their knowledge to new domains, or help others with this transfer via…
Many machine learning techniques rely on minimizing the covariance between output feature dimensions to extract minimally redundant representations from data. However, these methods do not eliminate all dependencies/redundancies, as…
Motivated by applications in databases, this paper considers various fragments of the calculus of binary relations. The fragments are obtained by leaving out, or keeping in, some of the standard operators, along with some derived operators…
Deep learning algorithms have increasingly been shown to lack robustness to simple adversarial examples (AdvX). An equally troubling observation is that these adversarial examples transfer between different architectures trained on…
Despite the recent advancements in deploying neural networks for image classification, it has been found that adversarial examples are able to fool these models leading them to misclassify the images. Since these models are now being widely…
We provide new statistical guarantees for transfer learning via representation learning--when transfer is achieved by learning a feature representation shared across different tasks. This enables learning on new tasks using far less data…
Domain adaptation seeks to leverage the abundant label information in a source domain to improve classification performance in a target domain with limited labels. While the field has seen extensive methodological development, its…
The morphological systems of natural languages are replete with examples of the same devices used for multiple purposes: (1) the same type of morphological process (for example, suffixation for both noun case and verb tense) and (2)…
In this paper we argue that, to its detriment, transparency research overlooks many foundational concepts of artificial intelligence. As an illustrating example we focus on uncertainty quantification in the context of counterfactual…