With the development of machine learning, expectations for artificial intelligence (AI) technology are increasing day by day. In particular, deep learning has shown enriched performance results in a variety of fields. There are many applications that are closely related to our daily life, such as making significant decisions in application area based on predictions or classifications, in which a deep learning (DL) model could be relevant. Hence, if a DL model causes mispredictions or misclassifications due to malicious external influences, it can cause very large difficulties in real life. Moreover, training deep learning models involves relying on an enormous amount of data and the training data often includes sensitive information. Therefore, deep learning models should not expose the privacy of such data. In this paper, we reviewed the threats and developed defense methods on the security of the models and the data privacy under the notion of SPAI: Secure and Private AI. We also discuss current challenges and open issues.

Coreference Resolution is the task of identifying groups of phrases in a text that refer to the same discourse entity. Such referring phrases are called mentions, a set of mentions that all refer to the same 1 discourse entity is called a coreference chain. Annotated corpora are important resources for developing and evaluating automatic coreference resolution methods. Turkish is an agglutinative language and Turkish coreference resolution poses several challenges different from many other languages, in particular the absence of grammatical gender, the possibility of null pronouns in subject and object position, possessive pronouns that can be expressed as suffixes, and ambiguities among possessive and number morphemes, e.g., 'çocukları' can be analysed as'their children' or as'his/her children', depending on context Oflazer and Bozşahin (1994). No coreference resolution corpus exists for Turkish so far. We here describe the result of an effort to create such a corpus based on the METU-Sabanci Turkish Treebank (Say, Zeyrek, Oflazer, and Özge, 2004; Atalay, Oflazer, and Say, 2003; Oflazer, Say, Hakkani-Tür, and Tür, 2003) which is, to the best of our knowledge, the only publicly available Turkish Treebank. Our contributions are as follows.

Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these classifiers arrive at a particular decision. Although many approaches have been proposed, a comprehensive understanding of the achievements and challenges is still lacking. This paper provides a survey covering existing techniques and methods to increase the interpretability of machine learning models and also discusses the crucial issues to consider in future work such as interpretation design principles and evaluation metrics in order to push forward the area of interpretable machine learning.

Monitoring of disasters is crucial for mitigating their effects on the environment and human population, and can be facilitated by the use of unmanned aerial vehicles (UAV), equipped with camera sensors that produce aerial photos of the areas of interest. A modern technique for recognition of events based on aerial photos is deep learning. In this paper, we present the state of the art work related to the use of deep learning techniques for disaster identification. We demonstrate the potential of this technique in identifying disasters with high accuracy, by means of a relatively simple deep learning model. Based on a dataset of 544 images (containing disaster images such as fires, earthquakes, collapsed buildings, tsunami and flooding, as well as non-disaster scenes), our results show an accuracy of 91% achieved, indicating that deep learning, combined with UAV equipped with camera sensors, have the potential to predict disasters with high accuracy.

Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech synthesis systems. Such neural networks are being used as an alternative to vocoders and hence they are often called neural vocoders. The neural vocoder uses acoustic features as local condition parameters, and these parameters need to be accurately predicted by another acoustic model. However, it is not yet clear how to train this acoustic model, which is problematic because the final quality of synthetic speech is significantly affected by the performance of the acoustic model. Significant degradation happens, especially when predicted acoustic features have mismatched characteristics compared to natural ones. In order to reduce the mismatched characteristics between natural and generated acoustic features, we propose frameworks that incorporate either a conditional generative adversarial network (GAN) or its variant, Wasserstein GAN with gradient penalty (WGAN-GP), into multi-speaker speech synthesis that uses the WaveNet vocoder. We also extend the GAN frameworks and use the discretized mixture logistic loss of a well-trained WaveNet in addition to mean squared error and adversarial losses as parts of objective functions. Experimental results show that acoustic models trained using the WGAN-GP framework using back-propagated discretized-mixture-of-logistics (DML) loss achieves the highest subjective evaluation scores in terms of both quality and speaker similarity.

Deep Neutral Networks(DNN) require huge GPU memory when training on modern image/video databases. Unfortunately, the GPU memory is always finite, which limits the image resolution, batch size, and learning rate that could be tuned for better performances. In this paper, we propose a novel approach, called Re-forwarding, that substantially reduces memory usage in training. Our approach only saves the tensors at a subset of layers during the first forward, and conduct extra local forwards (the Re-forwarding process) to compute the missing tensors needed during backward. The total memory cost becomes the sum of (1) the cost at the subset of layers and (2) the maximum cost of the re-forwarding processes. We propose theories and algorithms that achieve the optimal memory solutions for DNNs with either linear or arbitrary optimization graphs. Experiments show that Re-forwarding cut down huge amount of training memory on all popular DNNs such as Alexnet, VGG net, ResNet, Densenet and Inception net.

It's still early days in creating the kind of human-like androids we see in the movies, but new research brings us ever closer to the idea. Boston Dynamics has become the de facto image of locomotion for both humans and their pets, while LG already has its CLOi porter'bots and DARPA is working on centaur-like designs for disaster relief. Now, researchers at the Elon Musk-founded OpenAI are working on making robot hands more dextrous. According to a blog post, the team has trained a human-like robot hand called the Shadow Dextrous Hand to manipulate real-world objects like a child's block. It uses the same algorithms and code from its OpenAI Five project, which has been training DOTA 2 bots to play video games.

With over 25 years of experience in product management and marketing, business process, and manufacturing engineering, Tony helps organizations infuse the power of deep learning to solve their ...

In-hand manipulation is one of those things that's fairly high on the list of "skills that are effortless for humans but extraordinarily difficult for robots." Without even really thinking about it, we're able to adaptively coordinate four fingers and a thumb with our palm and friction and gravity to move things around in one hand without using our other hand--you've probably done this a handful (heh) of times today already, just with your cellphone. It takes us humans years of practice to figure out how to do in-hand manipulation robustly, but robots don't have that kind of time. Learning through practice and experience is still the way to go for complex tasks like this, and the challenge is finding a way to learn faster and more efficiently than just giving a robot hand something to manipulate over and over until it learns what works and what doesn't, which would probably take about a hundred years. Rather than wait a hundred years, researchers at OpenAI have used reinforcement learning to train a convolutional neural network to control a five-fingered Shadow hand to manipulate objects, all in just 50 hours.

Elon Musk is kinda worried about AI. ("AI is a fundamental existential risk for human civilization and I don't think people fully appreciate that," as he put it in 2017.) So he helped found a research nonprofit, OpenAI, to help cut a path to "safe" artificial general intelligence, as opposed to machines that pop our civilization like a pimple. Yes, Musk's very public fears may distract from other more real problems in AI. But OpenAI just took a big step toward robots that better integrate into our world by not, well, breaking everything they pick up. OpenAI researchers have built a system in which a simulated robotic hand learns to manipulate a block through trial and error, then seamlessly transfers that knowledge to a robotic hand in the real world.