Fujitsu Laboratories Ltd. announced the development of a technology to make AI models more robust against deception attacks. The technology protects against attempts to use forged attack data to trick AI models into making a deliberate misjudgment when AI is used for sequential data consisting of multiple elements. With the use of AI technologies progressing in various fields in recent years, the risk of attacks that intentionally interfere with AI's ability to make correct judgments represents a source of growing concern. Many suitable conventional security resistance enhancement technologies exist for media data like images and sound. Their application to sequential data such as communication logs and service usage history remains insufficient, however, because of the challenges posed by preparing simulated attack data and the loss of accuracy.

Random Reshuffling (RR) is an algorithm for minimizing finite-sum functions that utilizes iterative gradient descent steps in conjunction with data reshuffling. Often contrasted with its sibling Stochastic Gradient Descent (SGD), RR is usually faster in practice and enjoys significant popularity in convex and non-convex optimization. The convergence rate of RR has attracted substantial attention recently and, for strongly convex and smooth functions, it was shown to converge faster than SGD if 1) the stepsize is small, 2) the gradients are bounded, and 3) the number of epochs is large. We remove these 3 assumptions, improve the dependence on the condition number from $\kappa^2$ to $\kappa$ (resp. from $\kappa$ to $\sqrt{\kappa}$) and, in addition, show that RR has a different type of variance. We argue through theory and experiments that the new variance type gives an additional justification of the superior performance of RR. To go beyond strong convexity, we present several results for non-strongly convex and non-convex objectives. We show that in all cases, our theory improves upon existing literature. Finally, we prove fast convergence of the Shuffle-Once (SO) algorithm, which shuffles the data only once, at the beginning of the optimization process. Our theory for strongly-convex objectives tightly matches the known lower bounds for both RR and SO and substantiates the common practical heuristic of shuffling once or only a few times. As a byproduct of our analysis, we also get new results for the Incremental Gradient algorithm (IG), which does not shuffle the data at all.

Planning safe trajectories under uncertain and dynamic conditions makes the autonomous driving problem significantly complex. Current sampling-based methods such as Rapidly Exploring Random Trees (RRTs) are not ideal for this problem because of the high computational cost. Supervised learning methods such as Imitation Learning lack generalization and safety guarantees. To address these problems and in order to ensure a robust framework, we propose a Hierarchical Reinforcement Learning (HRL) structure combined with a Proportional-Integral-Derivative (PID) controller for trajectory planning. HRL helps divide the task of autonomous vehicle driving into sub-goals and supports the network to learn policies for both high-level options and low-level trajectory planner choices. The introduction of sub-goals decreases convergence time and enables the policies learned to be reused for other scenarios. In addition, the proposed planner is made robust by guaranteeing smooth trajectories and by handling the noisy perception system of the ego-car. The PID controller is used for tracking the waypoints, which ensures smooth trajectories and reduces jerk. The problem of incomplete observations is handled by using a Long-Short-Term-Memory (LSTM) layer in the network. Results from the high-fidelity CARLA simulator indicate that the proposed method reduces convergence time, generates smoother trajectories, and is able to handle dynamic surroundings and noisy observations.

This article is an introductory work towards a larger research framework relative to Scientific Prediction. It is a mixed between science and philosophy of science, therefore we can talk about Experimental Philosophy of Science. As a first result, we introduce a new forecasting method based on image completion, named Forecasting Method by Image Inpainting (FM2I). In fact, time series forecasting is transformed into fully images- and signal-based processing procedures. After transforming a time series data into its corresponding image, the problem of data forecasting becomes essentially a problem of image inpainting problem, i.e., completing missing data in the image. An extensive experimental evaluation is conducted using a large dataset proposed by the well-known M3-competition. Results show that FM2I represents an efficient and robust tool for time series forecasting. It has achieved prominent results in terms of accuracy and outperforms the best M3 forecasting methods.

We present the results and findings of the First Nuanced Arabic Dialect Identification Shared Task (NADI). This Shared Task includes two subtasks: country-level dialect identification (Subtask 1) and province-level sub-dialect identification (Subtask 2). The data for the shared task covers a total of 100 provinces from 21 Arab countries and are collected from the Twitter domain. As such, NADI is the first shared task to target naturally-occurring fine-grained dialectal text at the sub-country level. A total of 61 teams from 25 countries registered to participate in the tasks, thus reflecting the interest of the community in this area. We received 47 submissions for Subtask 1 from 18 teams and 9 submissions for Subtask 2 from 9 teams.

Explaining the predictions of neural black-box models is an important problem, especially when such models are used in applications where user trust is crucial. Estimating the influence of training examples on a learned neural model's behavior allows us to identify training examples most responsible for a given prediction and, therefore, to faithfully explain the output of a black-box model. The most generally applicable existing method is based on influence functions, which scale poorly for larger sample sizes and models. We propose gradient rollback, a general approach for influence estimation, applicable to neural models where each parameter update step during gradient descent touches a smaller number of parameters, even if the overall number of parameters is large. Neural matrix factorization models trained with gradient descent are part of this model class. These models are popular and have found a wide range of applications in industry. Especially knowledge graph embedding methods, which belong to this class, are used extensively. We show that gradient rollback is highly efficient at both training and test time. Moreover, we show theoretically that the difference between gradient rollback's influence approximation and the true influence on a model's behavior is smaller than known bounds on the stability of stochastic gradient descent. This establishes that gradient rollback is robustly estimating example influence. We also conduct experiments which show that gradient rollback provides faithful explanations for knowledge base completion and recommender datasets.

Graphs are data structures that are useful to represent ubiquitous phenomena, such as social networks, chemical molecules and recommendation systems. One of their strengths lies in the fact that they explicitly model relations (i.e. We can illustrate the added value of this data enrichment using the Cora citation network. This dataset contains a bag-of-words representation for a few hundred papers and the citation relations between each of these papers. If we apply dimensionality reduction (t-SNE) to create a 2D plot of the bag-of-words representations (Figure 1, left), we can see clusters (they are colored according to their research topic) arise but they overlap.

Pope Francis has urged Catholics to pray that artificial intelligence (AI) does not rebel against humankind. The pontiff, who made the appeal in his prayer intention for November, warned against rising inequality that could result from advanced robotics, and instead called for AI to work for everyone. "Artificial intelligence is at the heart of the epochal change we are experiencing," Francis said. "Robotics can make a better world possible if it is joined to the common good. "Indeed, if technological progress increases inequalities, it is not true progress.

Min-max optimization of an objective function $f: \mathbb{R}^d \times \mathbb{R}^d \rightarrow \mathbb{R}$ is an important model for robustness in an adversarial setting, with applications to many areas including optimization, economics, and deep learning. In many of these applications $f$ may be nonconvex-nonconcave, and finding a global min-max point may be computationally intractable. There is a long line of work that seeks computationally tractable algorithms for alternatives to the min-max optimization model. However, many of the alternative models have solution points which are only guaranteed to exist under strong assumptions on $f$, such as convexity, monotonicity, or special properties of the starting point. In this paper, we propose an optimization model, the $\varepsilon$-greedy adversarial equilibrium, which can serve as a computationally tractable alternative to the min-max optimization model. Roughly, we say a point $(x^\star, y^\star)$ is an $\varepsilon$-greedy adversarial equilibrium if $y^\star$ is an $\varepsilon$-approximate local maximum for $f(x^\star,\cdot)$, and $x^\star$ is an $\varepsilon$-approximate local minimum for a "greedy approximation" to the function $\max_z f(x, z)$ which can be efficiently estimated using second-order optimization algorithms. The existence follows from an algorithm that converges from any starting point to such a point in a number of evaluations to $f$, $\nabla_{y} f(x,y)$, and $\nabla^2_y f(x,y)$, that is polynomial in $1/\varepsilon$, the dimension $d$, and the bounds on $f$ and its Lipschitz constant. In addition to existence, our model retains many desirable properties of the min-max model. For instance, it empowers the min-player to make updates that take into account the max-player's response, and in the case of strong convexity/concavity it corresponds to a global min-max solution with duality gap $O(\epsilon^2)$.

We explore end-to-end trained differentiable models that integrate natural logic with neural networks, aiming to keep the backbone of natural language reasoning based on the natural logic formalism while introducing subsymbolic vector representations and neural components. The proposed model adapts module networks to model natural logic operations, which is enhanced with a memory component to model contextual information. Experiments show that the proposed framework can effectively model monotonicity-based reasoning, compared to the baseline neural network models without built-in inductive bias for monotonicity-based reasoning. Our proposed model shows to be robust when transferred from upward to downward inference. We perform further analyses on the performance of the proposed model on aggregation, showing the effectiveness of the proposed subcomponents on helping achieve better intermediate aggregation performance.