Earlier this month, a federal district court issued the first judicial decision in the country addressing whether an AI system can be an "inventor" under U.S. patent law. The decision was rendered by the U.S. District Court for the Eastern District of Virginia in Thaler v. Hirshfeld on appeal from the U.S. Patent and Trademark Office's (USPTO) decision that refused to allow Thaler's two patent applications to proceed because he listed DABUS (an AI machine) as the inventor. Thaler filed the applications in 2018--one for an invention used to contain food and the other for a flashing beacon for attracting attention in emergencies. In statements filed in support of the applications, Thaler listed DABUS as the inventor, claiming that he had acquired the right to the grant of the patents by "ownership of the creativity machine." In affirming the USPTO's denial of the applications, the court held that based on the plain statutory language of the U.S. Patent Act and Federal Circuit authority, an AI machine cannot be an inventor because an inventor must be an "individual," which under common interpretation and court precedent means a natural person. The court stated that Thaler's argument was based on policy considerations and the purpose of the patent clause of the U.S. Constitution, and that the decision to expand the scope of inventorship is squarely within the authority of Congress.

In many spatial trajectory-based applications, it is necessary to map raw trajectory data points onto road networks in digital maps, which is commonly referred to as a map-matching process. While most previous map-matching methods have focused on using rule-based algorithms to deal with the map-matching problems, in this paper, we consider the map-matching task from the data-driven perspective, proposing a deep learning-based map-matching model. We build a Transformer-based map-matching model with a transfer learning approach. We generate trajectory data to pre-train the Transformer model and then fine-tune the model with a limited number of ground-truth data to minimize the model development cost and reduce the real-to-virtual gap. Three metrics (Average Hamming Distance, F-score, and BLEU) at two levels (point and segment level) are used to evaluate the model performance. The results indicate that the proposed model outperforms existing models. Furthermore, we use the attention weights of the Transformer to plot the map-matching process and find how the model matches the road segments correctly.

Currently, an increasing number of model pruning methods are proposed to resolve the contradictions between the computer powers required by the deep learning models and the resource-constrained devices. However, most of the traditional rule-based network pruning methods can not reach a sufficient compression ratio with low accuracy loss and are time-consuming as well as laborious. In this paper, we propose Automatic Block-wise and Channel-wise Network Pruning (ABCP) to jointly search the block-wise and channel-wise pruning action with deep reinforcement learning. A joint sample algorithm is proposed to simultaneously generate the pruning choice of each residual block and the channel pruning ratio of each convolutional layer from the discrete and continuous search space respectively. The best pruning action taking both the accuracy and the complexity of the model into account is obtained finally. Compared with the traditional rule-based pruning method, this pipeline saves human labor and achieves a higher compression ratio with lower accuracy loss. Tested on the mobile robot detection dataset, the pruned YOLOv3 model saves 99.5% FLOPs, reduces 99.5% parameters, and achieves 37.3 times speed up with only 2.8% mAP loss. The results of the transfer task on the sim2real detection dataset also show that our pruned model has much better robustness performance.

Learning a near optimal policy in a partially observable system remains an elusive challenge in contemporary reinforcement learning. In this work, we consider episodic reinforcement learning in a reward-mixing Markov decision process (MDP). There, a reward function is drawn from one of multiple possible reward models at the beginning of every episode, but the identity of the chosen reward model is not revealed to the agent. Hence, the latent state space, for which the dynamics are Markovian, is not given to the agent. We study the problem of learning a near optimal policy for two reward-mixing MDPs. Unlike existing approaches that rely on strong assumptions on the dynamics, we make no assumptions and study the problem in full generality. Indeed, with no further assumptions, even for two switching reward-models, the problem requires several new ideas beyond existing algorithmic and analysis techniques for efficient exploration. We provide the first polynomial-time algorithm that finds an $\epsilon$-optimal policy after exploring $\tilde{O}(poly(H,\epsilon^{-1}) \cdot S^2 A^2)$ episodes, where $H$ is time-horizon and $S, A$ are the number of states and actions respectively. This is the first efficient algorithm that does not require any assumptions in partially observed environments where the observation space is smaller than the latent state space.

While the availability of large datasets is perceived to be a key requirement for training deep neural networks, it is possible to train such models with relatively little data. However, compensating for the absence of large datasets demands a series of actions to enhance the quality of the existing samples and to generate new ones. This paper summarizes our winning submission to the "Data-Centric AI" competition. We discuss some of the challenges that arise while training with a small dataset, offer a principled approach for systematic data quality enhancement, and propose a GAN-based solution for synthesizing new data points. Our evaluations indicate that the dataset generated by the proposed pipeline offers 5% accuracy improvement while being significantly smaller than the baseline.

Data stream classification has become a major research topic due to the increase in temporal data. One of the biggest hurdles of data stream classification is the development of algorithms that deal with evolving data, also known as concept drifts. As data changes over time, static prediction models lose their validity. Adapting to concept drifts provides more robust and better performing models. The Broad Learning System (BLS) is an effective broad neural architecture recently developed for incremental learning. BLS cannot provide instant response since it requires huge data chunks and is unable to handle concept drifts. We propose a Broad Ensemble Learning System (BELS) for stream classification with concept drift. BELS uses a novel updating method that greatly improves best-in-class model accuracy. It employs a dynamic output ensemble layer to address the limitations of BLS. We present its mathematical derivation, provide comprehensive experiments with 11 datasets that demonstrate the adaptability of our model, including a comparison of our model with BLS, and provide parameter and robustness analysis on several drifting streams, showing that it statistically significantly outperforms seven state-of-the-art baselines. We show that our proposed method improves on average 44% compared to BLS, and 29% compared to other competitive baselines.

Popular off-policy deep reinforcement learning algorithms compensate for overestimation bias during temporal-difference learning by utilizing pessimistic estimates of the expected target returns. In this work, we propose a novel learnable penalty to enact such pessimism, based on a new way to quantify the critic's epistemic uncertainty. Furthermore, we propose to learn the penalty alongside the critic with dual TD-learning, a strategy to estimate and minimize the bias magnitude in the target returns. Our method enables us to accurately counteract overestimation bias throughout training without incurring the downsides of overly pessimistic targets. Empirically, by integrating our method and other orthogonal improvements with popular off-policy algorithms, we achieve state-of-the-art results in continuous control tasks from both proprioceptive and pixel observations.

Aspect-based sentiment analysis (ABSA) is an NLP task that entails processing user-generated reviews to determine (i) the target being evaluated, (ii) the aspect category to which it belongs, and (iii) the sentiment expressed towards the target and aspect pair. In this article, we propose transforming ABSA into an abstract summary-like conditional text generation task that uses targets, aspects, and polarities to generate auxiliary statements. To demonstrate the efficacy of our task formulation and a proposed system, we fine-tune a pre-trained model for conditional text generation tasks to get new state-of-the-art results on a few restaurant domains and urban neighborhoods domain benchmark datasets.

We introduce SMProbLog, a generalization of the probabilistic logic programming language ProbLog. A ProbLog program defines a distribution over logic programs by specifying for each clause the probability that it belongs to a randomly sampled program, and these probabilities are mutually independent. The semantics of ProbLog is given by the success probability of a query, which corresponds to the probability that the query succeeds in a randomly sampled program. It is well-defined when each random sample uniquely determines the truth values of all logical atoms. Argumentation problems, however, represent an interesting practical application where this is not always the case. SMProbLog generalizes the semantics of ProbLog to the setting where multiple truth assignments are possible for a randomly sampled program, and implements the corresponding algorithms for both inference and learning tasks. We then show how this novel framework can be used to reason about probabilistic argumentation problems. Therefore, the key contribution of this paper are: a more general semantics for ProbLog programs, its implementation into a probabilistic programming framework for both inference and parameter learning, and a novel approach to probabilistic argumentation problems based on such framework.

Statistical divergences (SDs), which quantify the dissimilarity between probability distributions, are a basic constituent of statistical inference and machine learning. A modern method for estimating those divergences relies on parametrizing an empirical variational form by a neural network (NN) and optimizing over parameter space. Such neural estimators are abundantly used in practice, but corresponding performance guarantees are partial and call for further exploration. In particular, there is a fundamental tradeoff between the two sources of error involved: approximation and empirical estimation. While the former needs the NN class to be rich and expressive, the latter relies on controlling complexity. We explore this tradeoff for an estimator based on a shallow NN by means of non-asymptotic error bounds, focusing on four popular $\mathsf{f}$-divergences -- Kullback-Leibler, chi-squared, squared Hellinger, and total variation. Our analysis relies on non-asymptotic function approximation theorems and tools from empirical process theory. The bounds reveal the tension between the NN size and the number of samples, and enable to characterize scaling rates thereof that ensure consistency. For compactly supported distributions, we further show that neural estimators with a slightly different NN growth-rate are near minimax rate-optimal, achieving the parametric convergence rate up to logarithmic factors.