Since Google's artificial intelligence (AI) subsidiary DeepMind published a paper a few weeks ago describing a generalist agent they call Gato (which can perform various tasks using the same trained model) and claimed that artificial general intelligence (AGI) can be achieved just via sheer scaling, a heated debate has ensued within the AI community. While it may seem somewhat academic, the reality is that if AGI is just around the corner, our society--including our laws, regulations, and economic models--is not ready for it. Indeed, thanks to the same trained model, generalist agent Gato is capable of playing Atari, captioning images, chatting, or stacking blocks with a real robot arm. It can also decide, based on its context, whether to output text, join torques, button presses, or other tokens. As such, it does seem a much more versatile AI model than the popular GPT-3, DALL-E 2, PaLM, or Flamingo, which are becoming extremely good at very narrow specific tasks, such as natural language writing, language understanding, or creating images from descriptions.
This Artificial Intelligence tutorial provides basic and intermediate information on concepts of Artificial Intelligence. It is designed to help students and working professionals who are complete beginners. In this tutorial, our focus will be on artificial intelligence, if you wish to learn more about machine learning, you can check out this tutorial for complete beginners tutorial of Machine Learning. Through the course of this Artificial Intelligence tutorial, we will look at various concepts such as the meaning of artificial intelligence, the levels of AI, why AI is important, it's various applications, the future of artificial intelligence, and more. Usually, to work in the field of AI, you need to have a lot of experience. Thus, we will also discuss the various job profiles which are associated with artificial intelligence and will eventually help you to attain relevant experience. You don't need to be from a specific background before joining the field of AI as it is possible to learn and attain the skills needed. While the terms Data Science, Artificial Intelligence (AI) and Machine learning fall in the same domain and are connected, they have their specific applications and meaning. Simply put, artificial intelligence aims at enabling machines to execute reasoning by replicating human intelligence. Since the main objective of AI processes is to teach machines from experience, feeding the right information and self-correction is crucial. The answer to this question would depend on who you ask. A layman, with a fleeting understanding of technology, would link it to robots. If you ask about artificial intelligence to an AI researcher, (s)he would say that it's a set of algorithms that can produce results without having to be explicitly instructed to do so. Both of these answers are right.
Pedestrian trajectory forecasting is a fundamental task in multiple utility areas, such as self-driving, autonomous robots, and surveillance systems. The future trajectory forecasting is multi-modal, influenced by physical interaction with scene contexts and intricate social interactions among pedestrians. The mainly existing literature learns representations of social interactions by deep learning networks, while the explicit interaction patterns are not utilized. Different interaction patterns, such as following or collision avoiding, will generate different trends of next movement, thus, the awareness of social interaction patterns is important for trajectory forecasting. Moreover, the social interaction patterns are privacy concerned or lack of labels. To jointly address the above issues, we present a social-dual conditional variational auto-encoder (Social-DualCVAE) for multi-modal trajectory forecasting, which is based on a generative model conditioned not only on the past trajectories but also the unsupervised classification of interaction patterns. After generating the category distribution of the unlabeled social interaction patterns, DualCVAE, conditioned on the past trajectories and social interaction pattern, is proposed for multi-modal trajectory prediction by latent variables estimating. A variational bound is derived as the minimization objective during training. The proposed model is evaluated on widely used trajectory benchmarks and outperforms the prior state-of-the-art methods.
Autonomous robots and vehicles are expected to soon become an integral part of our environment. Unsatisfactory issues regarding interaction with existing road users, performance in mixed-traffic areas and lack of interpretable behavior remain key obstacles. To address these, we present a physics-based neural network, based on a hybrid approach combining a social force model extended by group force (SFMG) with Multi-Layer Perceptron (MLP) to predict pedestrian trajectories considering its interaction with static obstacles, other pedestrians and pedestrian groups. We quantitatively and qualitatively evaluate the model with respect to realistic prediction, prediction performance and prediction "interpretability". Initial results suggest, the model even when solely trained on a synthetic dataset, can predict realistic and interpretable trajectories with better than state-of-the-art accuracy.
When explaining AI behavior to humans, how is the communicated information being comprehended by the human explainee, and does it match what the explanation attempted to communicate? When can we say that an explanation is explaining something? We aim to provide an answer by leveraging theory of mind literature about the folk concepts that humans use to understand behavior. We establish a framework of social attribution by the human explainee, which describes the function of explanations: the concrete information that humans comprehend from them. Specifically, effective explanations should be coherent (communicate information which generalizes to other contrast cases), complete (communicating an explicit contrast case, objective causes, and subjective causes), and interactive (surfacing and resolving contradictions to the generalization property through iterations). We demonstrate that many XAI mechanisms can be mapped to folk concepts of behavior. This allows us to uncover their modes of failure that prevent current methods from explaining effectively, and what is necessary to enable coherent explanations.
Algorithms based on deep network models are being used for many pattern recognition and decision-making tasks in robotics and AI. Training these models requires a large labeled dataset and considerable computational resources, which are not readily available in many domains. Also, it is difficult to explore the internal representations and reasoning mechanisms of these models. As a step towards addressing the underlying knowledge representation, reasoning, and learning challenges, the architecture described in this paper draws inspiration from research in cognitive systems. As a motivating example, we consider an assistive robot trying to reduce clutter in any given scene by reasoning about the occlusion of objects and stability of object configurations in an image of the scene. In this context, our architecture incrementally learns and revises a grounding of the spatial relations between objects and uses this grounding to extract spatial information from input images. Non-monotonic logical reasoning with this information and incomplete commonsense domain knowledge is used to make decisions about stability and occlusion. For images that cannot be processed by such reasoning, regions relevant to the tasks at hand are automatically identified and used to train deep network models to make the desired decisions. Image regions used to train the deep networks are also used to incrementally acquire previously unknown state constraints that are merged with the existing knowledge for subsequent reasoning. Experimental evaluation performed using simulated and real-world images indicates that in comparison with baselines based just on deep networks, our architecture improves reliability of decision making and reduces the effort involved in training data-driven deep network models.
Vogelstein, Joshua T., Verstynen, Timothy, Kording, Konrad P., Isik, Leyla, Krakauer, John W., Etienne-Cummings, Ralph, Ogburn, Elizabeth L., Priebe, Carey E., Burns, Randal, Kutten, Kwame, Knierim, James J., Potash, James B., Hartung, Thomas, Smirnova, Lena, Worley, Paul, Savonenko, Alena, Phillips, Ian, Miller, Michael I., Vidal, Rene, Sulam, Jeremias, Charles, Adam, Cowan, Noah J., Bichuch, Maxim, Venkataraman, Archana, Li, Chen, Thakor, Nitish, Kebschull, Justus M, Albert, Marilyn, Xu, Jinchong, Shuler, Marshall Hussain, Caffo, Brian, Ratnanather, Tilak, Geisa, Ali, Roh, Seung-Eon, Yezerets, Eva, Madhyastha, Meghana, How, Javier J., Tomita, Tyler M., Dey, Jayanta, Ningyuan, null, Huang, null, Shin, Jong M., Kinfu, Kaleab Alemayehu, Chaudhari, Pratik, Baker, Ben, Schapiro, Anna, Jayaraman, Dinesh, Eaton, Eric, Platt, Michael, Ungar, Lyle, Wehbe, Leila, Kepecs, Adam, Christensen, Amy, Osuagwu, Onyema, Brunton, Bing, Mensh, Brett, Muotri, Alysson R., Silva, Gabriel, Puppo, Francesca, Engert, Florian, Hillman, Elizabeth, Brown, Julia, White, Chris, Yang, Weiwei
Research on both natural intelligence (NI) and artificial intelligence (AI) generally assumes that the future resembles the past: intelligent agents or systems (what we call 'intelligence') observe and act on the world, then use this experience to act on future experiences of the same kind. We call this 'retrospective learning'. For example, an intelligence may see a set of pictures of objects, along with their names, and learn to name them. A retrospective learning intelligence would merely be able to name more pictures of the same objects. We argue that this is not what true intelligence is about. In many real world problems, both NIs and AIs will have to learn for an uncertain future. Both must update their internal models to be useful for future tasks, such as naming fundamentally new objects and using these objects effectively in a new context or to achieve previously unencountered goals. This ability to learn for the future we call 'prospective learning'. We articulate four relevant factors that jointly define prospective learning. Continual learning enables intelligences to remember those aspects of the past which it believes will be most useful in the future. Prospective constraints (including biases and priors) facilitate the intelligence finding general solutions that will be applicable to future problems. Curiosity motivates taking actions that inform future decision making, including in previously unmet situations. Causal estimation enables learning the structure of relations that guide choosing actions for specific outcomes, even when the specific action-outcome contingencies have never been observed before. We argue that a paradigm shift from retrospective to prospective learning will enable the communities that study intelligence to unite and overcome existing bottlenecks to more effectively explain, augment, and engineer intelligences.
Opponent modeling is the ability to use prior knowledge and observations in order to predict the behavior of an opponent. This survey presents a comprehensive overview of existing opponent modeling techniques for adversarial domains, many of which must address stochastic, continuous, or concurrent actions, and sparse, partially observable payoff structures. We discuss all the components of opponent modeling systems, including feature extraction, learning algorithms, and strategy abstractions. These discussions lead us to propose a new form of analysis for describing and predicting the evolution of game states over time. We then introduce a new framework that facilitates method comparison, analyze a representative selection of techniques using the proposed framework, and highlight common trends among recently proposed methods. Finally, we list several open problems and discuss future research directions inspired by AI research on opponent modeling and related research in other disciplines.
This is Part II of the two-part comprehensive survey devoted to a computing framework most commonly known under the names Hyperdimensional Computing and Vector Symbolic Architectures (HDC/VSA). Both names refer to a family of computational models that use high-dimensional distributed representations and rely on the algebraic properties of their key operations to incorporate the advantages of structured symbolic representations and vector distributed representations. Holographic Reduced Representations is an influential HDC/VSA model that is well-known in the machine learning domain and often used to refer to the whole family. However, for the sake of consistency, we use HDC/VSA to refer to the area. Part I of this survey covered foundational aspects of the area, such as historical context leading to the development of HDC/VSA, key elements of any HDC/VSA model, known HDC/VSA models, and transforming input data of various types into high-dimensional vectors suitable for HDC/VSA. This second part surveys existing applications, the role of HDC/VSA in cognitive computing and architectures, as well as directions for future work. Most of the applications lie within the machine learning/artificial intelligence domain, however we also cover other applications to provide a thorough picture. The survey is written to be useful for both newcomers and practitioners.