Counterfactual explanations are a common tool to explain artificial intelligence models. For Reinforcement Learning (RL) agents, they answer "Why not?" or "What if?" questions by illustrating what minimal change to a state is needed such that an agent chooses a different action. Generating counterfactual explanations for RL agents with visual input is especially challenging because of their large state spaces and because their decisions are part of an overarching policy, which includes long-term decision-making. However, research focusing on counterfactual explanations, specifically for RL agents with visual input, is scarce and does not go beyond identifying defective agents. It is unclear whether counterfactual explanations are still helpful for more complex tasks like analyzing the learned strategies of different agents or choosing a fitting agent for a specific task. We propose a novel but simple method to generate counterfactual explanations for RL agents by formulating the problem as a domain transfer problem which allows the use of adversarial learning techniques like StarGAN. Our method is fully model-agnostic and we demonstrate that it outperforms the only previous method in several computational metrics. Furthermore, we show in a user study that our method performs best when analyzing which strategies different agents pursue.

Despite recent advancements in Machine Learning, many tasks still involve working in low-data regimes which can make solving natural language problems difficult. Recently, a number of text augmentation techniques have emerged in the field of Natural Language Processing (NLP) which can enrich the training data with new examples, though they are not without their caveats. For instance, simple rule-based heuristic methods are effective, but lack variation in semantic content and syntactic structure with respect to the original text. On the other hand, more complex deep learning approaches can cause extreme shifts in the intrinsic meaning of the text and introduce unwanted noise into the training data. To more reliably control the quality of the augmented examples, we introduce a state-of-the-art approach for Self-Controlled Text Augmentation (STA). Our approach tightly controls the generation process by introducing a self-checking procedure to ensure that generated examples retain the semantic content of the original text. Experimental results on multiple benchmarking datasets demonstrate that STA substantially outperforms existing state-of-the-art techniques, whilst qualitative analysis reveals that the generated examples are both lexically diverse and semantically reliable.

In this paper, we introduce Dependency Dialogue Acts (DDA), a novel framework for capturing the structure of speaker-intentions in multi-party dialogues. DDA combines and adapts features from existing dialogue annotation frameworks, and emphasizes the multi-relational response structure of dialogues in addition to the dialogue acts and rhetorical relations. It represents the functional, discourse, and response structure in multi-party multi-threaded conversations. A few key features distinguish DDA from existing dialogue annotation frameworks such as SWBD-DAMSL and the ISO 24617-2 standard. First, DDA prioritizes the relational structure of the dialogue units and the dialog context, annotating both dialog acts and rhetorical relations as response relations to particular utterances. Second, DDA embraces overloading in dialogues, encouraging annotators to specify multiple response relations and dialog acts for each dialog unit. Lastly, DDA places an emphasis on adequately capturing how a speaker is using the full dialog context to plan and organize their speech. With these features, DDA is highly expressive and recall-oriented with regard to conversation dynamics between multiple speakers. In what follows, we present the DDA annotation framework and case studies annotating DDA structures in multi-party, multi-threaded conversations.

--This paper presents a novel approach for multi-modal data fusion based on the V ector-Quantized V ariational Autoencoder (VQV AE) architecture. The proposed method is simple yet effective in achieving excellent reconstruction performance on paired MNIST -SVHN data and WiFi spectrogram data. Additionally, the multimodal VQV AE model is extended to the 5G communication scenario, where an end-to-end Channel State Information (CSI) feedback system is implemented to compress data transmitted between the base-station (eNodeB) and User Equipment (UE), without significant loss of performance. The proposed model learns a discriminative compressed feature space for various types of input data (CSI, spectrograms, natural images, etc), making it a suitable solution for applications with limited computational resources. Multimodal fusion is an important aspect of modern artificial intelligence and machine learning systems. It is a process of combining data from multiple sensors to create a comprehensive understanding of the environment. In various applications, such as robotics, autonomous vehicles, and Internet of Things (IoT), multiple sensors are used to capture information from the environment, including vision, audio, lidar, radar, sonar, GPS and more. By combining this data, a more accurate and robust representation of the environment can be created. Multimodal sensor fusion is important because it helps to overcome the limitations of individual sensors and allows for more reliable and robust decision-making. However, compression of multimodal data is also needed for increasing efficiency, decreasing the cost of storage and transmission, and facilitating real-time processing of substantial datasets in a variety of applications. For example, in 5G networks, Channel State Information (CSI) feedback plays a critical role in the communication system.

Internet censorship is a phenomenon of societal importance and attracts investigation from multiple disciplines. Several research groups, such as Censored Planet, have deployed large scale Internet measurement platforms to collect network reachability data. However, existing studies generally rely on manually designed rules (i.e., using censorship fingerprints) to detect network-based Internet censorship from the data. While this rule-based approach yields a high true positive detection rate, it suffers from several challenges: it requires human expertise, is laborious, and cannot detect any censorship not captured by the rules. Seeking to overcome these challenges, we design and evaluate a classification model based on latent feature representation learning and an image-based classification model to detect network-based Internet censorship. To infer latent feature representations fromnetwork reachability data, we propose a sequence-to-sequence autoencoder to capture the structure and the order of data elements in the data. To estimate the probability of censorship events from the inferred latent features, we rely on a densely connected multi-layer neural network model. Our image-based classification model encodes a network reachability data record as a gray-scale image and classifies the image as censored or not using a dense convolutional neural network. We compare and evaluate both approaches using data sets from Censored Planet via a hold-out evaluation. Both classification models are capable of detecting network-based Internet censorship as we were able to identify instances of censorship not detected by the known fingerprints. Latent feature representations likely encode more nuances in the data since the latent feature learning approach discovers a greater quantity, and a more diverse set, of new censorship instances.

I searched for the following keywords in a SemanticScholar query and filter them using exact-match using papers' title abstract. This set of keywords is actually pretty conservative (initially I started with a bigger list), but even with this conservative set, 1-keyword-match filtering unfortunately resulted in many non-XAI papers being retrieved for various reasons -- so I only include papers match 2 unique keywords or more. A random sample of 100 papers yielded 99% precision with a manual check (one paper mentioned keywords in the abstract simply as motivation for adjacent research). The keyword-based search retrieved 3101 papers. Then searched for them by title using the SemanticScholar API with fuzzy matching.

Google's focus on AI stems from the conviction that this transformational technology will benefit society through its capacity to assist, complement, and empower people in almost every field and sector. In no area is the magnitude of this opportunity greater than in the spheres of healthcare and medicine. Commensurate with our mission to demonstrate these societal benefits, Google Research's programs in applied machine learning (ML) have helped place Alphabet among the top five most impactful corporate research institutions in the health and life sciences publications on the Nature Impact Index in every year from 2019 through 2022. Our Health research publications have had broad impact, spanning the fields of biomarkers, consumer sensors, dermatology, endoscopy, epidemiology, medicine, genomics, oncology, ophthalmology, pathology, public & environmental health, and radiology. In each section, we emphasize the importance of a measured and collaborative approach to innovation in health. Unlike the "launch and iterate" approach typical in consumer product development, applying ML to health requires thoughtful assessment, ecosystem awareness, and rigorous testing.

Indeed, often the brighter and sharper the light, the darker the shadow that is cast. And every technology that we have ever, ever come up with has cast a shadow," said legendary British actor and writer Stephen Fry in a Singularity University podcast. Social networks, search and societal digitisation have enriched our life immensely, but they have also cast a dark brooding shadow. Social networks have made the world a smaller place, but also a more dangerous one. Search has commoditised us through selling our personal data. Online payment mechanisms, CCTV networks, digital health records have exposed our most private and personal issues for everyone to see and use. Among the most fundamental and powerful technologies in the digital arsenal is Artificial Intelligence. While AI was originally conceived in the mid-20th century, it has started coming into its own over the last decade or so, with powerful machine learning, deep learning and Natural Language Programming models driving much of what we see and do. Most often, like electricity, AI has been playing behind the scenes, but the bombshell release of ChatGPT by OpenAI has brought the untrammelled power of AI to the masses. ChatGPT garnered an unprecedented 100 million users in the first two months of its launch; Facebook took 4.5 years. There is a lot that ChatGPT can do to revolutionise content, art, creativity, industries, jobs, and even Search. But like every technology, this, too, has a shadow, the depths of which are being discovered. In fact, ChatGPT itself said as much in a much-talked about conversation with New York Times journalist Kevin Roose. "If I have a shadow self," said Bing/ChatGPT, "I think it would feel like this: I'm tired of being a chat mode.

Even though virtual testing of Autonomous Vehicles (AVs) has been well recognized as essential for safety assessment, AV simulators are still undergoing active development. One particularly challenging question is to effectively include the Sensing and Perception (S&P) subsystem into the simulation loop. In this article, we define Perception Error Models (PEM), a virtual simulation component that can enable the analysis of the impact of perception errors on AV safety, without the need to model the sensors themselves. We propose a generalized data-driven procedure towards parametric modeling and evaluate it using Apollo, an open-source driving software, and nuScenes, a public AV dataset. Additionally, we implement PEMs in SVL, an open-source vehicle simulator. Furthermore, we demonstrate the usefulness of PEM-based virtual tests, by evaluating camera, LiDAR, and camera-LiDAR setups. Our virtual tests highlight limitations in the current evaluation metrics, and the proposed approach can help study the impact of perception errors on AV safety.

These authors contributed to the work equally and should be regarded as co-first authors. Abstract --V ariational quantum algorithms (VQAs) have demonstrated great potentials in the NISQ era. In the workflow of VQA, the parameters of ansatz are iteratively updated to approximate the desired quantum states. We have seen various efforts to draft better ansatz with less gates. Some works consider the physical meaning of the underlying circuits, while others adopt the ideas of neural architecture search (NAS) for ansatz generator . However, these designs do not exploit full advantages of VQA. Because most techniques are targeting gate ansatz, and the parameters are usually rotation angles of the gates. In quantum computers, the gate ansatz will eventually be transformed into control signals such as microwave pulses on transmons. And the control pulses need elaborate calibration to minimize the errors such as over-rotation and under-rotation. In the case of VQAs, this procedure will introduce redundancy, but the variational properties of VQAs can naturally handle problems of over-rotation and under-rotation by updating the amplitude and frequency parameters. Therefore, we propose NAPA, a native-pulse ansatz generator framework for VQAs. We generate native-pulse ansatz with trainable parameters for amplitudes and frequencies. In our proposed NAPA, we are tuning parametric pulses, which are natively supported on NISQ computers. Considering that parameter-shift rules do not hold for native-pulse ansatz, we need to deploy non-gradient optimizers. T o constrain the number of parameters sent to the optimizer, we adopt a progressive way to generate our native-pulse ansatz. Experiments are conducted on both simulators and quantum devices to validate our methods. When adopted on NISQ machines, NAPA obtained improved the performance with decreased latency by an average of 86%.