Reviewing the history of the development of artificial intelligence (AI) clearly reveals that brain science has resulted in breakthroughs in AI, such as deep learning. At present, although the developmental trend in AI and its applications has surpassed expectations, an insurmountable gap remains between AI and human intelligence. It is urgent to establish a bridge between brain science and AI research, including a link from brain science to AI, and a connection from knowing the brain to simulating the brain. The first steps toward this goal are to explore the secrets of brain science by studying new brain-imaging technology; to establish a dynamic connection diagram of the brain; and to integrate neuroscience experiments with theory, models, and statistics. Based on these steps, a new generation of AI theory and methods can be studied, and a subversive model and working mode from machine perception and learning to machine thinking and decision-making can be established. This article discusses the opportunities and challenges of adapting brain science to AI.
Causal inference is a powerful modeling tool for explanatory analysis, which might enable current machine learning to become explainable. How to marry causal inference with machine learning to develop eXplainable Artificial Intelligence (XAI) algorithms is one of key steps towards to the artificial intelligence 2.0. With the aim of bringing knowledge of causal inference to scholars of machine learning
and artificial intelligence, we invited researchers working on causal inference to write this survey from different aspects of causal inference. This survey includes the following sections: ″Estimating average treatment effect: A brief review and beyond″ from Dr. Kun Kuang, ″Attribution problems in counterfactual inference″ from Prof. Lian Li, ″The Yule-Simpson paradox and the surrogate paradox″ from Prof. Zhi Geng, ″Causal potential theory″ from Prof. Lei Xu, ″Discovering causal information from observational data″ from Prof. Kun Zhang, ″Formal argumentation in causal reasoning and explanation″ from Profs. Beishui Liao and Huaxin Huang, ″Causal inference with complex experiments″ from Prof. Peng Ding, ″Instrumental variables and negative controls for observational studies″ from Prof. Wang Miao, and ″Causal inference with interference″ from Dr. Zhichao Jiang.
Recently, due to the availability of big data and the rapid growth of computing power, artificial intelligence (AI) has regained tremendous attention and investment. Machine learning (ML) approaches have been successfully applied to solve many problems in academia and in industry. Although the explosion of big data applications is driving the development of ML, it also imposes severe challenges of data processing speed and scalability on conventional computer systems. Computing platforms that are dedicatedly designed for AI applications have been considered, ranging from a complement to von Neumann platforms to a “must-have” and standalone technical solution. These platforms, which belong to a larger category named “domain-specific computing,” focus on specific customization for AI. In this article, we focus on summarizing the recent advances in accelerator designs for deep neural networks (DNNs)—that is, DNN accelerators. We discuss various architectures that support DNN executions in terms of computing units, dataflow optimization, targeted network topologies, architectures on emerging technologies, and accelerators for emerging applications. We also provide our visions on the future trend of AI chip designs.
Natural language processing (NLP) is a subfield of artificial intelligence (AI) that focuses on enabling computers to understand and process human languages. In the last five years, we have witnessed the rapid development of NLP in tasks such as machine translation, question-answering, and machine reading comprehension based on deep learning and an enormous volume of annotated and unannotated data. In this paper, we will review the latest progress in the neural network-based NLP framework (neural NLP) from three perspectives: modeling, learning, and reasoning. In the modeling section, we will describe several fundamental neural network-based modeling paradigms, such as word embedding, sentence embedding, and sequence-to-sequence modeling, which are widely used in modern NLP engines. In the learning section, we will introduce widely used learning methods for NLP models, including supervised, semi-supervised, and unsupervised learning; multitask learning; transfer learning; and active learning. We view reasoning as a new and exciting direction for neural NLP, but it has yet to be well addressed. In the reasoning section, we will review reasoning mechanisms, including the knowledge, existing non-neural inference methods, and new neural inference methods. We emphasize the importance of reasoning in this paper because it is important for building interpretable and knowledge-driven neural NLP models to handle complex tasks. At the end of this paper, we will briefly outline our thoughts on the future directions of neural NLP.
Artificial intelligence (AI) has been developing rapidly in recent years in terms of software algorithms, hardware implementation, and applications in a vast number of areas. In this review, we summarize the latest developments of applications of AI in biomedicine, including disease diagnostics, living assistance, biomedical information processing, and biomedical research. The aim of this review is to keep track of new scientific accomplishments, to understand the availability of technologies, to appreciate the tremendous potential of AI in biomedicine, and to provide researchers in related fields with inspiration. It can be asserted that, just like AI itself, the application of AI in biomedicine is still in its early stage. New progress and breakthroughs will continue to push the frontier and widen the scope of AI application, and fast developments are envisioned in the near future. Two case studies are provided to illustrate the prediction of epileptic seizure occurrences and the filling of a dysfunctional urinary bladder.
Ethics and governance are vital to the healthy and sustainable development of artificial intelligence (AI). With the long-term goal of keeping AI beneficial to human society, governments, research organizations, and companies in China have published ethical guidelines and principles for AI, and have launched projects to develop AI governance technologies. This paper presents a survey of these efforts and highlights the preliminary outcomes in China. It also describes the major research challenges in AI governance research and discusses future research directions.
Recent progress in deep learning is essentially based on a “big data for small tasks” paradigm, under which massive amounts of data are used to train a classifier for a single narrow task. In this paper, we call for a shift that flips this paradigm upside down. Specifically, we propose a “small data for big tasks” paradigm, wherein a single artificial intelligence (AI) system is challenged to develop “common sense,” enabling it to solve a wide range of tasks with little training data. We illustrate the potential power of this new paradigm by reviewing models of common sense that synthesize recent breakthroughs in both machine and human vision. We identify functionality, physics, intent, causality, and utility (FPICU) as the five core domains of cognitive AI with humanlike common sense. When taken as a unified concept, FPICU is concerned with the questions of “why” and “how,” beyond the dominant “what” and “where” framework for understanding vision. They are invisible in terms of pixels but nevertheless drive the creation, maintenance, and development of visual scenes. We therefore coin them the “dark matter” of vision. Just as our universe cannot be understood by merely studying observable matter, we argue that vision cannot be understood without studying FPICU. We demonstrate the power of this perspective to develop cognitive AI systems with humanlike common sense by showing how to observe and apply FPICU with little training data to solve a wide range of challenging tasks, including tool use, planning, utility inference, and social learning. In summary, we argue that the next generation of AI must embrace “dark” humanlike common sense for solving novel tasks.
With the rapid developments of artificial intelligence (AI) and deep learning (DL) techniques, it is critical
to ensure the security and robustness of the deployed algorithms. Recently, the security vulnerability of
DL algorithms to adversarial samples has been widely recognized. The fabricated samples can lead to various
misbehaviors of the DL models while being perceived as benign by humans. Successful implementations
of adversarial attacks in real physical-world scenarios further demonstrate their practicality.
Hence, adversarial attack and defense techniques have attracted increasing attention from both machine
learning and security communities and have become a hot research topic in recent years. In this paper,
we first introduce the theoretical foundations, algorithms, and applications of adversarial attack techniques.
We then describe a few research efforts on the defense techniques, which cover the broad frontier
in the field. Several open problems and challenges are subsequently discussed, which we hope will provoke
further research efforts in this critical area.
This work introduces an optimal transportation (OT) view of generative adversarial networks (GANs). Natural datasets have intrinsic patterns, which can be summarized as the manifold distribution principle: the distribution of a class of data is close to a low-dimensional manifold. GANs mainly accomplish two tasks: manifold learning and probability distribution transformation. The latter can be carried out using the classical OT method. From the OT perspective, the generator computes the OT map, while the discriminator computes the Wasserstein distance between the generated data distribution and the real data distribution; both can be reduced to a convex geometric optimization process. Furthermore, OT theory discovers the intrinsic collaborative—instead of competitive—relation between the generator and the discriminator, and the fundamental reason for mode collapse. We also propose a novel generative model, which uses an autoencoder (AE) for manifold learning and OT map for probability distribution transformation. This AE–OT model improves the theoretical rigor and transparency, as well as the computational stability and efficiency; in particular, it eliminates the mode collapse. The experimental results validate our hypothesis, and demonstrate the advantages of our proposed model.