As neural network classifiers are deployed in real-world applications, it is crucial that their predictions are not just accurate, but trustworthy as well. One practical solution is to assign confidence scores to each prediction, then filter out lowconfidence predictions. However, existing confidence metrics are not yet sufficiently reliable for this role. This paper presents a new framework that produces more reliable confidence scores for detecting misclassification errors. This framework, RED, calibrates the classifier's inherent confidence indicators and estimates uncertainty of the calibrated confidence scores using Gaussian Processes. Empirical comparisons with other confidence estimation methods on 125 UCI datasets demonstrate that this approach is effective. An experiment on a vision task with a large deep learning architecture further confirms that the method can scale up, and a case study involving out-of-distribution and adversarial samples shows potential of the proposed method to improve robustness of neural network classifiers more broadly in the future. Classifiers based on Neural Networks (NNs) are widely deployed in many real-world applications (LeCun et al., 2015; Anjos et al., 2015; Alghoul et al., 2018; Shahid et al., 2019). Although good prediction accuracies are achieved, lack of safety guarantees becomes a severe issue when NNs are applied to safety-critical domains, e.g., healthcare (Selişteanu et al., 2018; Gupta et al., 2007; Shahid et al., 2019), finance (Dixon et al., 2017), self-driving (Janai et al., 2017; Hecker et al., 2018), etc. One way to estimate trustworthiness of a classifier prediction is to use its inherent confidence-related score, e.g., the maximum class probability (Hendrycks & Gimpel, 2017), entropy of the softmax outputs (Williams & Renals, 1997), or difference between the highest and second highest activation outputs (Monteith & Martinez, 2010).

We deal with the problem of generating textual captions from optical remote sensing (RS) images using the notion of deep reinforcement learning. Due to the high inter-class similarity in reference sentences describing remote sensing data, jointly encoding the sentences and images encourages prediction of captions that are semantically more precise than the ground truth in many cases. To this end, we introduce an Actor Dual-Critic training strategy where a second critic model is deployed in the form of an encoder-decoder RNN to encode the latent information corresponding to the original and generated captions. While all actor-critic methods use an actor to predict sentences for an image and a critic to provide rewards, our proposed encoder-decoder RNN guarantees high-level comprehension of images by sentence-to-image translation. We observe that the proposed model generates sentences on the test data highly similar to the ground truth and is successful in generating even better captions in many critical cases. Extensive experiments on the benchmark Remote Sensing Image Captioning Dataset (RSICD) and the UCM-captions dataset confirm the superiority of the proposed approach in comparison to the previous state-of-the-art where we obtain a gain of sharp increments in both the ROUGE-L and CIDEr measures.

Most of existing deep learning models rely on excessive amounts of labeled training data in order to achieve state-of-the-art results, even though these data can be hard or costly to get in practice. One attractive alternative is to learn with little supervision, commonly referred to as few-shot learning (FSL), and, in particular, meta-learning that learns to learn with few data from related tasks. Despite the practical success of meta-learning, many of its algorithmic solutions proposed in the literature are based on sound intuitions, but lack a solid theoretical analysis of the expected performance on the test task. In this paper, we review the recent advances in meta-learning theory and show how they can be used in practice both to better understand the behavior of popular meta-learning algorithms and to improve their generalization capacity. This latter is achieved by integrating the theoretical assumptions ensuring efficient meta-learning in the form of regularization terms into several popular meta-learning algorithms for which we provide a large study of their behavior on classic few-shot classification benchmarks. To the best of our knowledge, this is the first contribution that puts the most recent learning bounds of meta-learning theory into practice for the popular task of few-shot classification.

Torchattacks is a PyTorch (Paszke et al. 2019) library that contains adversarial attacks to generate adversarial examples and to verify the robustness of deep learning models. Since Szegedy et al. (2013) found that deep learning models are vulnerable to the perturbed examples with small noises, called adversarial examples, various adversarial attacks have been continuously proposed. In this technical report, we provide a list of implemented adversarial attacks and explain the algorithms of each method. Here are some important things to check before generating adversarial examples. To make it easy to use adversarial attacks, a reverse-normalization is not included in the attack process.

Recently, cyber-attacks have been extensively seen due to the everlasting increase of malware in the cyber world. These attacks cause irreversible damage not only to end-users but also to corporate computer systems. Ransomware attacks such as WannaCry and Petya specifically targets to make critical infrastructures such as airports and rendered operational processes inoperable. Hence, it has attracted increasing attention in terms of volume, versatility, and intricacy. The most important feature of this type of malware is that they change shape as they propagate from one computer to another. Since standard signature-based detection software fails to identify this type of malware because they have different characteristics on each contaminated computer. This paper aims at providing an image augmentation enhanced deep convolutional neural network (CNN) models for the detection of malware families in a metamorphic malware environment. The main contributions of the paper's model structure consist of three components, including image generation from malware samples, image augmentation, and the last one is classifying the malware families by using a convolutional neural network model. In the first component, the collected malware samples are converted binary representation to 3-channel images using windowing technique. The second component of the system create the augmented version of the images, and the last component builds a classification model. In this study, five different deep convolutional neural network model for malware family detection is used.

In the Open Data era, a large number of table resources have been made available on the Web and data portals. However, it is difficult to directly utilize such data due to the ambiguity of entities, name variations, heterogeneous schema, missing, or incomplete metadata. To address these issues, we propose a novel approach, namely TabEAno, to semantically annotate table rows toward knowledge graph entities. Specifically, we introduce a "two-cells" lookup strategy bases on the assumption that there is an existing logical relation occurring in the knowledge graph between the two closed cells in the same row of the table. Despite the simplicity of the approach, TabEAno outperforms the state of the art approaches in the two standard datasets e.g, T2D, Limaye with, and in the large-scale Wikipedia tables dataset.

Class-imbalance is one of the major challenges in real world datasets, where a few classes (called majority classes) constitute much more data samples than the rest (called minority classes). Learning deep neural networks using such datasets leads to performances that are typically biased towards the majority classes. Most of the prior works try to solve class-imbalance by assigning more weights to the minority classes in various manners (e.g., data re-sampling, cost-sensitive learning). However, we argue that the number of available training data may not be always a good clue to determine the weighting strategy because some of the minority classes might be sufficiently represented even by a small number of training data. Overweighting samples of such classes can lead to drop in the model's overall performance. We claim that the 'difficulty' of a class as perceived by the model is more important to determine the weighting. In this light, we propose a novel loss function named Class-wise Difficulty-Balanced loss, or CDB loss, which dynamically distributes weights to each sample according to the difficulty of the class that the sample belongs to. Note that the assigned weights dynamically change as the 'difficulty' for the model may change with the learning progress. Extensive experiments are conducted on both image (artificially induced class-imbalanced MNIST, long-tailed CIFAR and ImageNet-LT) and video (EGTEA) datasets. The results show that CDB loss consistently outperforms the recently proposed loss functions on class-imbalanced datasets irrespective of the data type (i.e., video or image).

Table entailment, the binary classification task of finding if a sentence is supported or refuted by the content of a table, requires parsing language and table structure as well as numerical and discrete reasoning. While there is extensive work on textual entailment, table entailment is less well studied. We adapt TAPAS (Herzig et al., 2020), a table-based BERT model, to recognize entailment. Motivated by the benefits of data augmentation, we create a balanced dataset of millions of automatically created training examples which are learned in an intermediate step prior to fine-tuning. This new data is not only useful for table entailment, but also for SQA (Iyyer et al., 2017), a sequential table QA task. To be able to use long examples as input of BERT models, we evaluate table pruning techniques as a pre-processing step to drastically improve the training and prediction efficiency at a moderate drop in accuracy. The different methods set the new state-of-the-art on the TabFact (Chen et al., 2020) and SQA datasets.

State-of-the-art attacks on NLP models lack a shared definition of a what constitutes a successful attack. We distill ideas from past work into a unified framework: a successful natural language adversarial example is a perturbation that fools the model and follows some linguistic constraints. We then analyze the outputs of two state-of-the-art synonym substitution attacks. We find that their perturbations often do not preserve semantics, and 38% introduce grammatical errors. Human surveys reveal that to successfully preserve semantics, we need to significantly increase the minimum cosine similarities between the embeddings of swapped words and between the sentence encodings of original and perturbed sentences.With constraints adjusted to better preserve semantics and grammaticality, the attack success rate drops by over 70 percentage points.

So you're interested in AI? Then join our online event, TNW2020, where you'll hear how artificial intelligence is transforming industries and businesses. The Game of Life is a grid-based automaton that is very popular in discussions about science, computation, and artificial intelligence. It is an interesting idea that shows how very simple rules can yield very complicated results. Despite its simplicity, however, the Game of Life remains a challenge to artificial neural networks, AI researchers at Swarthmore College and the Los Alamos National Laboratory have shown in a recent paper. Titled, "It's Hard for Neural Networks To Learn the Game of Life," their research investigates how neural networks explore the Game of Life and why they often miss finding the right solution.