Planning algorithms based on lookahead search have achieved remarkable successes in artificial intelligence. Human world champions have been defeated in classic games such as checkers [34], chess [5], Go [38] and poker [3, 26], and planning algorithms have had real-world impact in applications from logistics [47] to chemical synthesis [37]. However, these planning algorithms all rely on knowledge of the environment's dynamics, such as the rules of the game or an accurate simulator, preventing their direct application to real-world domains like robotics, industrial control, or intelligent assistants. Model-based reinforcement learning (RL) [42] aims to address this issue by first learning a model of the environment's dynamics, and then planning with respect to the learned model. Typically, these models have either focused on reconstructing the true environmental state [8, 16, 24], or the sequence of full observations [14, 20]. However, prior work [4, 14, 20] remains far from the state of the art in visually rich domains, such as Atari 2600 games [2]. Instead, the most successful methods are based on model-free RL [9, 21, 18] - i.e. they estimate the optimal policy and/or value function directly from interactions with the environment. However, model-free algorithms are in turn far from the state of the art in domains that require precise and sophisticated lookahead, such as chess and Go. In this paper, we introduce MuZero, a new approach to model-based RL that achieves state-of-the-art performance in Atari 2600, a visually complex set of domains, while maintaining superhuman performance in precision planning tasks such as chess, shogi and Go.

Deeper neural networks are hard to train. Inspired by the elastic collision model in physics, we present a universal structure that could be integrated into the existing network structures to speed up the training process and eventually increase its generalization ability. We apply our structure to the Con-volutional Neural Networks(CNNs) to form a new structure, which we term the "Interlayer Collision" (IC) structure. The IC structure provides the deeper layer a better representation of the input features. We evaluate the IC structure on CI-FAR10 and Imagenet by integrating it into the existing state-of-the-art CNNs. Our experiment shows that the proposed IC structure can effectively increase the accuracy and convergence speed.

A BSTRACT Recent advances in deep learning theory have evoked the study of generalizabil-ity across different local minima of deep neural networks (DNNs). While current work focused on either discovering properties of good local minima or developing regularization techniques to induce good local minima, no approach exists that can tackle both problems. We achieve these two goals successfully in a unified manner. Specifically, based on the Fisher information we propose a metric both strongly indicative of generalizability of local minima and effectively applied as a practical regularizer. We provide theoretical analysis including a generalization bound and empirically demonstrate the success of our approach in both capturing and improving the generalizability of DNNs. Experiments are performed on CIFAR-10 and CIFAR-100 for various network architectures. 1 I NTRODUCTION Recently, there has been a surge in the interest of acquiring a theoretical understanding over deep neural network's behavior. Breakthroughs have been made in characterizing the optimization process, showing that learning algorithms such as stochastic gradient descent (SGD) tend to end up in one of the many local minima which have close-to-zero training loss (Choromanska et al., 2015; Dauphin et al., 2014; Kawaguchi, 2016; Nguyen & Hein, 2018; Du et al., 2018). It is, therefore, natural to ask two closely related questions: (a) What kind of local minima can generalize better? To our knowledge, existing work focused only on one of the two questions. For the "what" question, various definitions of "flatness/sharpness" have been introduced and analyzed (Keskar et al., 2017; Neyshabur et al., 2018; 2017; Wu et al., 2017; Liang et al., 2017).

Current Neural Architecture Search techniques can suffer from a few shortcomings, including high computational cost, excessive bias from the search space, conceptual complexity or uncertain empirical benefits over random search. In this paper, we present ImmuNeCS, an attempt at addressing these issues with a method that offers a simple, flexible, and efficient way of building deep learning models automatically, and we demonstrate its effectiveness in the context of convolutional neural networks. Instead of searching for the 1-best architecture for a given task, we focus on building a population of neural networks that are then ensembled into a neural network committee, an approach we dub 'Neural Committee Search'. To ensure sufficient performance from the committee, our search algorithm is based on an artificial immune system that balances individual performance with population diversity. This allows us to stop the search when accuracy starts to plateau, and to bridge the performance gap through ensembling. In order to justify our method, we first verify that the chosen search space exhibits the locality property. To further improve efficiency, we also combine partial evaluation, weight inheritance, and progressive search. First, experiments are run to verify the validity of these techniques. Then, preliminary experimental results on two popular computer vision benchmarks show that our method consistently outperforms random search and yields promising results within reasonable GPU budgets. An additional experiment also shows that ImmuNeCS's solutions transfer effectively to a more difficult task, where they achieve results comparable to a direct search on the new task. We believe these findings can open the way for new, accessible alternatives to traditional NAS.

Despite remarkable advances in automated visual recognition by machines, some visual tasks remain challenging for machines. Fleuret et al. (2011) introduced the Synthetic Visual Reasoning Test (SVRT) to highlight this point, which required classification of images consisting of randomly generated shapes based on hidden abstract rules using only a few examples. Ellis et al. (2015) demonstrated that a program synthesis approach could solve some of the SVRT problems with unsupervised, few-shot learning, whereas they remained challenging for several convolutional neural networks trained with thousands of examples. Here we re-considered the human and machine experiments, because they followed different protocols and yielded different statistics. We thus proposed a quantitative reintepretation of the data between the protocols, so that we could make fair comparison between human and machine performance. We improved the program synthesis classifier by correcting the image parsings, and compared the results to the performance of other machine agents and human subjects. We grouped the SVRT problems into different types by the two aspects of the core characteristics for classification: shape specification and location relation. We found that the program synthesis classifier could not solve problems involving shape distances, because it relied on symbolic computation which scales poorly with input dimension and adding distances into such computation would increase the dimension combinatorially with the number of shapes in an image. Therefore, although the program synthesis classifier is capable of abstract reasoning, its performance is highly constrained by the accessible information in image parsings.

Diagnosing basal cell carcinomas (BCC), one of the most common cutaneous malignancies in humans, is a task regularly performed by pathologists and dermato-pathologists. Improving histological diagnosis by providing diagnosis suggestions, i.e. computer-assisted diagnoses is actively researched to improve safety, quality and efficiency. Increasingly, machine learning methods are applied due to their superior performance. However, typical images obtained by scanning histological sections often have a resolution that is prohibitive for processing with current state-of-the-art neural networks. Furthermore, the data pose a problem of weak labels, since only a tiny fraction of the image is indicative of the disease class, whereas a large fraction of the image is highly similar to the non-disease class. The aim of this study is to evaluate whether it is possible to detect basal cell carcinomas in histological sections using attention-based deep learning models and to overcome the ultra-high resolution and the weak labels of whole slide images. We demonstrate that attention-based models can indeed yield almost perfect classification performance with an AUC of 0.95.

Inappropriate and profane content on social media is exponentially increasing and big corporations are becoming more aware of the type of content on which they are advertising and how it may affect their brand reputation. But with a huge surge in content being posted online it becomes seemingly difficult to filter out related videos on which they can run their ads without compromising brand name. Advertising on youtube videos generates a huge amount of revenue for corporations. It becomes increasingly important for such corporations to advertise on only the videos that don't hurt the feelings, community or harmony of the audience at large. In this paper, we propose a system to identify inappropriate content on YouTube and leverage it to perform a first of its kind, large scale, quantitative characterization that reveals some of the risks of YouTube ads consumption on inappropriate videos. Customization of the architecture have also been included to serve different requirements of corporations. Our analysis reveals that YouTube is still plagued by such disturbing videos and its currently deployed countermeasures are ineffective in terms of detecting them in a timely manner. Our framework tries to fill this gap by providing a handy, add on solution to filter the videos and help corporations and companies to push ads on the platform without worrying about the content on which the ads are displayed.

--Wide spread of satirical news in online communities is an ongoing trend. The nature of satires are so inherently ambiguous that sometimes it's too hard even for humans to understand whether it's actually satire or not. So, research interest has grown in this field. The purpose of this research is to detect Bangla satirical news spread in online news portals as well as social media. In this paper we propose a hybrid technique for extracting feature from text documents combining Word2V ecand TF-IDF. Using our proposed feature extraction technique, with standard CNN architecture we could detect whether a Bangla text document is satire or not with an accuracy of more than 96%. Satires can be considered as a literary form which involves a delicate balance between criticism and humor.

Certain research strands can yield "forbidden knowledge". This term refers to knowledge that is considered too sensitive, dangerous or taboo to be produced or shared. Discourses about such publication restrictions are already entrenched in scientific fields like IT security, synthetic biology or nuclear physics research. This paper makes the case for transferring this discourse to machine learning research. Some machine learning applications can very easily be misused and unfold harmful consequences, for instance with regard to generative video or text synthesis, personality analysis, behavior manipulation, software vulnerability detection and the like. Up to now, the machine learning research community embraces the idea of open access. However, this is opposed to precautionary efforts to prevent the malicious use of machine learning applications. Information about or from such applications may, if improperly disclosed, cause harm to people, organizations or whole societies. Hence, the goal of this work is to outline norms that can help to decide whether and when the dissemination of such information should be prevented. It proposes review parameters for the machine learning community to establish an ethical framework on how to deal with forbidden knowledge and dual-use applications.

The integration of a Knowledge Base (KB) into a neural dialogue agent is one of the key challenges in Conversational AI. Memory networks has proven to be effective to encode KB information into an external memory to thus generate more fluent and informed responses. Unfortunately, such memory becomes full of latent representations during training, so the most common strategy is to overwrite old memory entries randomly. In this paper, we question this approach and provide experimental evidence showing that conventional memory networks generate many redundant latent vectors resulting in overfitting and the need for larger memories. We introduce memory dropout as an automatic technique that encourages diversity in the latent space by 1) Aging redundant memories to increase their probability of being overwritten during training 2) Sampling new memories that summarize the knowledge acquired by redundant memories. This technique allows us to incorporate Knowledge Bases to achieve state-of-the-art dialogue generation in the Stanford Multi-Turn Dialogue dataset. Considering the same architecture, its use provides an improvement of +2.2 BLEU points for the automatic generation of responses and an increase of +8.1% in the recognition of named entities.