2018年8月、Google BrainチームはTensorFlow 1.10をリリースし、Raspberry Pi（Raspbian）に正式対応しました。ラズベリーパイでディープラーニング・IoTにチャレンジしましょう！

MAKKAH: Artificial intelligence is an increasingly important part of modern life and the technologies we rely on, but it is also being used to enhance awareness and understanding of more traditional and long-established aspects of our lives and cultures. For example, AI is serving the Arabic language through its use in applications that support teaching and learning and assist in the development of dictionaries and programs to help millions of people worldwide to learn and use the language. Abdullah Al-Washmi, the secretary-general of the King Salman Global Academy for Arabic Language, told Arab News that the academy aims to become a global reference resource for the language by providing the tools required to promote, teach, learn and encourage the use of Arabic, in accordance with the objectives of the Kingdom's Vision 2030 and its Human Capability Development Program. Part of the academy's strategy involves a focus on accelerating the pace of technical research in various fields relating to the Arabic language, using AI tools to aid understanding, he added. AI has become a major enabler of the teaching and learning of languages, Al-Washmi said, by helping to provide multiple learning patterns that allow students to learn Arabic in ways tailored to their needs.

All human actions are based on anticipated futures. We cannot know the future because it does not exist yet, but we can use our current knowledge to imagine the future and make them happen. The better we understand the present and the history that has created it, the better we can understand the possibilities of the future. To appreciate the opportunities and challenges that artificial intelligence (AI) creates, we need both a good understanding of what AI is today and what the future may bring when AI is widely used in society. AI can enable new ways of learning, teaching, and education, and it may also change society in ways that pose new challenges for educational institutions.

Recent times are witnessing rapid development in machine learning algorithm systems, especially in reinforcement learning, natural language processing, computer and robot vision, image processing, speech, and emotional processing and understanding. In tune with the increasing importance and relevance of machine learning models, algorithms, and their applications, and with the emergence of more innovative uses cases of deep learning and artificial intelligence, the current volume presents a few innovative research works and their applications in real world, such as stock trading, medical and healthcare systems, and software automation. The chapters in the book illustrate how machine learning and deep learning algorithms and models are designed, optimized, and deployed. The volume will be useful for advanced graduate and doctoral students, researchers, faculty members of universities, practicing data scientists and data engineers, professionals, and consultants working on the broad areas of machine learning, deep learning, and artificial intelligence.

The similarity between objects is significant in a broad range of areas. While similarity can be measured using off-the-shelf distance functions, they may fail to capture the inherent meaning of similarity, which tends to depend on the underlying data and task. Moreover, conventional distance functions limit the space of similarity measures to be symmetric and do not directly allow comparing objects from different spaces. We propose using quantum networks (GQSim) for learning task-dependent (a)symmetric similarity between data that need not have the same dimensionality. We analyze the properties of such similarity function analytically (for a simple case) and numerically (for a complex case) and showthat these similarity measures can extract salient features of the data. We also demonstrate that the similarity measure derived using this technique is $(\epsilon,\gamma,\tau)$-good, resulting in theoretically guaranteed performance. Finally, we conclude by applying this technique for three relevant applications - Classification, Graph Completion, Generative modeling.

Autoencoders are the simplest neural network for unsupervised learning, and thus an ideal framework for studying feature learning. While a detailed understanding of the dynamics of linear autoencoders has recently been obtained, the study of non-linear autoencoders has been hindered by the technical difficulty of handling training data with non-trivial correlations - a fundamental prerequisite for feature extraction. Here, we study the dynamics of feature learning in non-linear, shallow autoencoders. We derive a set of asymptotically exact equations that describe the generalisation dynamics of autoencoders trained with stochastic gradient descent (SGD) in the limit of high-dimensional inputs. These equations reveal that autoencoders learn the leading principal components of their inputs sequentially. An analysis of the long-time dynamics explains the failure of sigmoidal autoencoders to learn with tied weights, and highlights the importance of training the bias in ReLU autoencoders. Building on previous results for linear networks, we analyse a modification of the vanilla SGD algorithm which allows learning of the exact principal components. Finally, we show that our equations accurately describe the generalisation dynamics of non-linear autoencoders on realistic datasets such as CIFAR10.

Linear prediction is the cornerstone of a significant group of statistical learning algorithms including linear regression, Support Vector Machines (SVM), regularized regressions (such as ridge, elastic net, lasso, and its variants), logistic regression, Poisson regression, probit models, single-layer perceptrons, and tensor regression, just to name a few. Thus, developing a deeper understanding of the pertinent linear prediction models and generalizing the methods to provide unified theoretical bounds is of critical importance to the machine learning community. For the past few decades, researchers have unveiled different aspects of these linear models. Bartlett and Shawe-Taylor (1999) obtained high confidence generalization error bounds for SVMs and other learning algorithms such as boosting and Bayesian posterior classifier. Vapnik-Chervonenkis (VC) theory (Vapnik, 2013) and Rademacher complexity (Bartlett and Mendelson, 2001, 2002) have been instrumental in the machine learning literature to provide generalization bounds (Shalev-Shwartz and Ben-David, 2014). Theoretical properties of the multiple-instance extensions of SVM were analyzed by Doran and Ray (2014). Joint first authors contributed equally to this work.

Effective human learning depends on a wide selection of educational materials that align with the learner's current understanding of the topic. While the Internet has revolutionized human learning or education, a substantial resource accessibility barrier still exists. Namely, the excess of online information can make it challenging to navigate and discover high-quality learning materials. In this paper, we propose the educational resource discovery (ERD) pipeline that automates web resource discovery for novel domains. The pipeline consists of three main steps: data collection, feature extraction, and resource classification. We start with a known source domain and conduct resource discovery on two unseen target domains via transfer learning. We first collect frequent queries from a set of seed documents and search on the web to obtain candidate resources, such as lecture slides and introductory blog posts. Then we introduce a novel pretrained information retrieval deep neural network model, query-document masked language modeling (QD-MLM), to extract deep features of these candidate resources. We apply a tree-based classifier to decide whether the candidate is a positive learning resource. The pipeline achieves F1 scores of 0.94 and 0.82 when evaluated on two similar but novel target domains. Finally, we demonstrate how this pipeline can benefit an application: leading paragraph generation for surveys. This is the first study that considers various web resources for survey generation, to the best of our knowledge. We also release a corpus of 39,728 manually labeled web resources and 659 queries from NLP, Computer Vision (CV), and Statistics (STATS).

Acquiring information on large areas on the earth's surface through satellite cameras allows us to see much more than we can see while standing on the ground. This assists us in detecting and monitoring the physical characteristics of an area like land-use patterns, atmospheric conditions, forest cover, and many unlisted aspects. The obtained images not only keep track of continuous natural phenomena but are also crucial in tackling the global challenge of severe deforestation. Among which Amazon basin accounts for the largest share every year. Proper data analysis would help limit detrimental effects on the ecosystem and biodiversity with a sustainable healthy atmosphere. This report aims to label the satellite image chips of the Amazon rainforest with atmospheric and various classes of land cover or land use through different machine learning and superior deep learning models. Evaluation is done based on the F2 metric, while for loss function, we have both sigmoid cross-entropy as well as softmax cross-entropy. Images are fed indirectly to the machine learning classifiers after only features are extracted using pre-trained ImageNet architectures. Whereas for deep learning models, ensembles of fine-tuned ImageNet pre-trained models are used via transfer learning. Our best score was achieved so far with the F2 metric is 0.927.

Generative Artificial Intelligence (AI) models are a compelling way to introduce K-12 students to AI education using an artistic medium, and hence have drawn attention from K-12 AI educators. Previous Creative AI curricula mainly focus on Generative Adversarial Networks (GANs) while paying less attention to Autoregressive Models, Variational Autoencoders (VAEs), or other generative models, which have since become common in the field of generative AI. VAEs' latent-space structure and interpolation ability could effectively ground the interdisciplinary learning of AI, creative arts, and philosophy. Thus, we designed a lesson to teach high school students about VAEs. We developed a web-based game and used Plato's cave, a philosophical metaphor, to introduce how VAEs work. We used a Google Colab notebook for students to re-train VAEs with their hand-written digits to consolidate their understandings. Finally, we guided the exploration of creative VAE tools such as SketchRNN and MusicVAE to draw the connection between what they learned and real-world applications. This paper describes the lesson design and shares insights from the pilot studies with 22 students. We found that our approach was effective in teaching students about a novel AI concept.