Cryptic crosswords, the dominant English-language crossword variety in the United Kingdom, can be solved by expert humans using flexible, creative intelligence and knowledge of language. Cryptic clues read like fluent natural language, but they are adversarially composed of two parts: a definition and a wordplay cipher requiring sub-word or character-level manipulations. As such, they are a promising target for evaluating and advancing NLP systems that seek to process language in more creative, human-like ways. We present a dataset of cryptic crossword clues from a major newspaper that can be used as a benchmark and train a sequence-to-sequence model to solve them. We also develop related benchmarks that can guide development of approaches to this challenging task. We show that performance can be substantially improved using a novel curriculum learning approach in which the model is pre-trained on related tasks involving, e.g, unscrambling words, before it is trained to solve cryptics. However, even this curricular approach does not generalize to novel clue types in the way that humans can, and so cryptic crosswords remain a challenge for NLP systems and a potential source of future innovation.

The past decade has witnessed a groundbreaking rise of machine learning for human language analysis, with current methods capable of automatically accurately recovering various aspects of syntax and semantics - including sentence structure and grounded word meaning - from large data collections. Recent research showed the promise of such tools for analyzing acoustic communication in nonhuman species. We posit that machine learning will be the cornerstone of future collection, processing, and analysis of multimodal streams of data in animal communication studies, including bioacoustic, behavioral, biological, and environmental data. Cetaceans are unique non-human model species as they possess sophisticated acoustic communications, but utilize a very different encoding system that evolved in an aquatic rather than terrestrial medium. Sperm whales, in particular, with their highly-developed neuroanatomical features, cognitive abilities, social structures, and discrete click-based encoding make for an excellent starting point for advanced machine learning tools that can be applied to other animals in the future. This paper details a roadmap toward this goal based on currently existing technology and multidisciplinary scientific community effort. We outline the key elements required for the collection and processing of massive bioacoustic data of sperm whales, detecting their basic communication units and language-like higher-level structures, and validating these models through interactive playback experiments. The technological capabilities developed by such an undertaking are likely to yield cross-applications and advancements in broader communities investigating non-human communication and animal behavioral research.

Time series with missing data are signals encountered in important settings for machine learning. Some of the most successful prior approaches for modeling such time series are based on recurrent neural networks that transform the input and previous state to account for the missing observations, and then treat the transformed signal in a standard manner. In this paper, we introduce a single unifying framework, Recursive Input and State Estimation (RISE), for this general approach and reformulate existing models as specific instances of this framework. We then explore additional novel variations within the RISE framework to improve the performance of any instance. We exploit representation learning techniques to learn latent representations of the signals used by RISE instances. We discuss and develop various encoding techniques to learn latent signal representations. We benchmark instances of the framework with various encoding functions on three data imputation datasets, observing that RISE instances always benefit from encoders that learn representations for numerical values from the digits into which they can be decomposed.

In model-based reinforcement learning (MBRL), Wan et al. (2019) showed conditions under which the environment model could produce the expectation of the next feature vector rather than the full distribution, or a sample thereof, with no loss in planning performance. Such expectation models are of interest when the environment is stochastic and non-stationary, and the model is approximate, such as when it is learned using function approximation. In these cases a full distribution model may be impractical and a sample model may be either more expensive computationally or of high variance. Wan et al. considered only planning for prediction to evaluate a fixed policy. In this paper, we treat the control case - planning to improve and find a good approximate policy. We prove that planning with an expectation model must update a state-value function, not an action-value function as previously suggested (e.g., Sorg & Singh, 2010). This opens the question of how planning influences action selections. We consider three strategies for this and present general MBRL algorithms for each. We identify the strengths and weaknesses of these algorithms in computational experiments. Our algorithms and experiments are the first to treat MBRL with expectation models in a general setting.

We propose a promising neural network model with which to acquire a grounded representation of robot actions and the linguistic descriptions thereof. Properly responding to various linguistic expressions, including polysemous words, is an important ability for robots that interact with people via linguistic dialogue. Previous studies have shown that robots can use words that are not included in the action-description paired datasets by using pre-trained word embeddings. However, the word embeddings trained under the distributional hypothesis are not grounded, as they are derived purely from a text corpus. In this letter, we transform the pre-trained word embeddings to embodied ones by using the robot's sensory-motor experiences. We extend a bidirectional translation model for actions and descriptions by incorporating non-linear layers that retrofit the word embeddings. By training the retrofit layer and the bidirectional translation model alternately, our proposed model is able to transform the pre-trained word embeddings to adapt to a paired action-description dataset. Our results demonstrate that the embeddings of synonyms form a semantic cluster by reflecting the experiences (actions and environments) of a robot. These embeddings allow the robot to properly generate actions from unseen words that are not paired with actions in a dataset.

Performance measures such as accuracy, recall, and precision, \(F_1\) Score.

Artificial intelligence (AI) has sped up the process of detecting flooded buildings immediately after a large-scale flood, allowing emergency personnel to direct their efforts efficiently. Now, a research group from Tohoku University has created a machine learning (ML) model that uses news media photos to identify flooded buildings accurately within 24 hours of the disaster. Their research was published in the journal Remote Sensing on April 5, 2021. "Our model demonstrates how the rapid reporting of news media can speed up and increase the accuracy of damage mapping activities, accelerating disaster relief and response decisions, said Shunichi Koshimura of Tohoku University's International Research Institute of Disaster Science and co-author of the study. ML and deep learning algorithms are tailored to classify objects through image analysis.

With the help of this list, any person who is interested in artificial intelligence or machine learning can feel free to learn all about it. In this course, the instructor is going to talk about the meaning behind the common AI terminology. It includes explanations about neural networks, machine learning, data science, and deep learning. Then the instructor will talk about what AI can and can't do realistically. Similarly, you will also get to understand how to spot opportunities to apply AI to different problems in your own organization.

AI learns from seen data to make predictions about unseen data. What is utterly remarkable is that prediction can underpin extraordinary creativity and mimicry. These developments have the potential to unleash an explosion of scale creativity -- delivering content design and production tools into the hands of the mass market that have hitherto only been available to large corporations with hefty budgets. Even now -- when we are still in the infancy of AI media generation -- there are demos, apps and subscription-based services to faceswap individuals into movies (see Zao), turn rough sketches into photorealistic images (try the GauGAN demo here), convert one voice into another (see Respeecher), personalise marketing videos (try the Synthesia demo here), age- and emotion-alter images (see Photoshop's new Neural Filters), generate face-synched videos of new or translated scripts (see Canny AI), play a video game with characters speaking any of 10 face-synched languages (see Cyberpunk 2077), and play a text-based adventure game with endless dialogue generated by AI (try out the free version of AI Dungeon here). Moreover, the same AI techniques will spawn new applications in a wide range of fields: advertising, architecture, interior design, gaming, song-writing, web design, education, even software development and pure mathematics -- in fact anywhere where structured or constrained creativity is key.

Have you ever thought about what would happen if you combined the power of machine learning and artificial intelligence with financial engineering? Today, you can stop imagining, and start doing. This course will teach you the core fundamentals of financial engineering, with a machine learning twist. We will learn about the greatest flub made in the past decade by marketers posing as "machine learning experts" who promise to teach unsuspecting students how to "predict stock prices with LSTMs". You will learn exactly why their methodology is fundamentally flawed and why their results are complete nonsense.