We introduce a machine learning approach to model checking temporal logic, with application to formal hardware verification. Model checking answers the question of whether every execution of a given system satisfies a desired temporal logic specification. Unlike testing, model checking provides formal guarantees. Its application is expected standard in silicon design and the EDA industry has invested decades into the development of performant symbolic model checking algorithms. Our new approach combines machine learning and symbolic reasoning by using neural networks as formal proof certificates for linear temporal logic. We train our neural certificates from randomly generated executions of the system and we then symbolically check their validity using satisfiability solving which, upon the affirmative answer, establishes that the system provably satisfies the specification. We leverage the expressive power of neural networks to represent proof certificates as well as the fact that checking a certificate is much simpler than finding one. As a result, our machine learning procedure for model checking is entirely unsupervised, formally sound, and practically effective. We experimentally demonstrate that our method outperforms the state-of-the-art academic and commercial model checkers on a set of standard hardware designs written in SystemVerilog.

Knowledge graph entity typing (KGET) aims to infer missing entity type instances in knowledge graphs. Previous research has predominantly centered around leveraging contextual information associated with entities, which provides valuable clues for inference. However, they have long ignored the dual nature of information inherent in entities, encompassing both high-level coarse-grained cluster knowledge and fine-grained type knowledge. This paper introduces Cross-view Optimal Transport for knowledge graph Entity Typing (COTET), a method that effectively incorporates the information on how types are clustered into the representation of entities and types. COTET comprises three modules: i) Multi-view Generation and Encoder, which captures structured knowledge at different levels of granularity through entity-type, entity-cluster, and type-cluster-type perspectives; ii) Cross-view Optimal Transport, transporting view-specific embeddings to a unified space by minimizing the Wasserstein distance from a distributional alignment perspective; iii) Pooling-based Entity Typing Prediction, employing a mixture pooling mechanism to aggregate prediction scores from diverse neighbors of an entity. Additionally, we introduce a distribution-based loss function to mitigate the occurrence of false negatives during training. Extensive experiments demonstrate the effectiveness of COTET when compared to existing baselines.

When tuning software configuration for better performance (e.g., latency or throughput), an important issue that many optimizers face is the presence of local optimum traps, compounded by a highly rugged configuration landscape and expensive measurements. To mitigate these issues, a recent effort has shifted to focus on the level of optimization model (called meta multi-objectivization or MMO) instead of designing better optimizers as in traditional methods. This is done by using an auxiliary performance objective, together with the target performance objective, to help the search jump out of local optima. While effective, MMO needs a fixed weight to balance the two objectives-a parameter that has been found to be crucial as there is a large deviation of the performance between the best and the other settings. However, given the variety of configurable software systems, the "sweet spot" of the weight can vary dramatically in different cases and it is not possible to find the right setting without time-consuming trial and error. In this paper, we seek to overcome this significant shortcoming of MMO by proposing a weight adaptation method, dubbed AdMMO. Our key idea is to adaptively adjust the weight at the right time during tuning, such that a good proportion of the nondominated configurations can be maintained. Moreover, we design a partial duplicate retention mechanism to handle the issue of too many duplicate configurations without losing the rich information provided by the "good" duplicates. Experiments on several real-world systems, objectives, and budgets show that, for 71% of the cases, AdMMO is considerably superior to MMO and a wide range of state-of-the-art optimizers while achieving generally better efficiency with the best speedup between 2.2x and 20x.

In presence of multiple objectives to be optimized in Search-Based Software Engineering (SBSE), Pareto search has been commonly adopted. It searches for a good approximation of the problem's Pareto optimal solutions, from which the stakeholders choose the most preferred solution according to their preferences. However, when clear preferences of the stakeholders (e.g., a set of weights which reflect relative importance between objectives) are available prior to the search, weighted search is believed to be the first choice since it simplifies the search via converting the original multi-objective problem into a single-objective one and enable the search to focus on what only the stakeholders are interested in. This paper questions such a "weighted search first" belief. We show that the weights can, in fact, be harmful to the search process even in the presence of clear preferences. Specifically, we conduct a large scale empirical study which consists of 38 systems/projects from three representative SBSE problems, together with two types of search budget and nine sets of weights, leading to 604 cases of comparisons. Our key finding is that weighted search reaches a certain level of solution quality by consuming relatively less resources at the early stage of the search; however, Pareto search is at the majority of the time (up to 77% of the cases) significantly better than its weighted counterpart, as long as we allow a sufficient, but not unrealistic search budget. This, together with other findings and actionable suggestions in the paper, allows us to codify pragmatic and comprehensive guidance on choosing weighted and Pareto search for SBSE under the circumstance that clear preferences are available. All code and data can be accessed at: https://github.com/ideas-labo/pareto-vs-weight-for-sbse.

Along with the great success of deep neural networks, there is also growing concern about their black-box nature. The interpretability issue affects people's trust on deep learning systems. It is also related to many ethical problems, e.g., algorithmic discrimination. Moreover, interpretability is a desired property for deep networks to become powerful tools in other research fields, e.g., drug discovery and genomics. In this survey, we conduct a comprehensive review of the neural network interpretability research. We first clarify the definition of interpretability as it has been used in many different contexts. Then we elaborate on the importance of interpretability and propose a novel taxonomy organized along three dimensions: type of engagement (passive vs. active interpretation approaches), the type of explanation, and the focus (from local to global interpretability). This taxonomy provides a meaningful 3D view of distribution of papers from the relevant literature as two of the dimensions are not simply categorical but allow ordinal subcategories. Finally, we summarize the existing interpretability evaluation methods and suggest possible research directions inspired by our new taxonomy.

Whether it's auto-extracting information from a scanned receipt for an expense report or translating a foreign language using your phone's camera, optical character recognition (OCR) technology can seem mesmerizing. And while it seems miraculous that we have computers that can digitize analog text with a degree of accuracy, the reality is that the accuracy we have come to expect falls short of what's possible. And that's because, despite the perception of OCR as an extraordinary leap forward, it's actually pretty old-fashioned and limited, largely because it's run by an oligopoly that's holding back further innovation. OCR's precursor was invented over 100 years ago in Birmingham, England by the scientist Edmund Edward Fournier d'Albe. Wanting to help blind people "read" text, d'Albe built a device, the Optophone, that used photo sensors to detect black print and convert it into sounds.

Whether it's auto-extracting information from a scanned receipt for an expense report or translating a foreign language using your phone's camera, optical character recognition (OCR) technology can seem mesmerizing. And while it seems miraculous that we have computers that can digitize analog text with a degree of accuracy, the reality is that the accuracy we have come to expect falls short of what's possible. And that's because, despite the perception of OCR as an extraordinary leap forward, it's actually pretty old-fashioned and limited, largely because it's run by an oligopoly that's holding back further innovation. OCR's precursor was invented over 100 years ago in Birmingham, England by the scientist Edmund Edward Fournier d'Albe. Wanting to help blind people "read" text, d'Albe built a device, the Optophone, that used photo sensors to detect black print and convert it into sounds.

Andrea Soltoggio received a combined BSc and MSc degree in Computer Science in 2004 from the Norwegian University of Science and Technology, Norway, and from Politecnico di Milano, Italy. He was awarded a Ph.D. in Computer Science in 2009 from the University of Birmingham, UK. He was with the Laboratory of Intelligent Systems at EPFL, Lausanne, CH, in 2006 and 2008-2009. He was a visiting researcher at the University of Central Florida, US, in 2009. From 2010 to 2014 he was Technical Coordinator of the FP7 European large-scale integration project AMARSi with the Research Institute for Cognition and Robotics, Bielefeld University, Germany.

In September 2015 we gave a talk at the Rezzed sessions of the EGX 2015 event in the NEC in Birmingham, UK. In this talk, we aimed at establishing'what' AI research is, why people do it and what are the big issues we are tackling in this modern day.

As part of the IEEE RAS International Conference on Humanoid Robots in Birmingham, U.K., last month, the awards committee decided to organize a fun photo contest. Participants submitted 39 photos showing off their humanoids in all kinds of poses and places. I was happy to be one of the judges, along with Sabine Hauert from the University of Bristol and Robohub, and with Giorgio Metta, the conference's awards chair, overseeing our selection. All photos were posted on Facebook and Twitter, and users were invited to vote on them. Sabine and I then looked at the photos with the most votes and scored them for originality, creativity, photo structure, and tech or fun factor. Here are the winners of the two categories, "Best Humanoid Photo" and "Best Funny Humanoid Photo," and all the amazing submissions.