The Conference on Neural Information Processing Systems (NIPS) took place between December 4th and 9th in Long Beach, CA, USA. As one of the top machine learning and computational neuroscience conferences, this year' s NIPS was a complete success experiencing an even larger rush of attendees compared to previous years. Apart from the rising number of participants, the conference has also seen a strong increase in submitted papers. Of the total 3240 papers submitted, 679 papers were accepted resulting in a 21% acceptance rate compared to last year's 24%. This is an indicator of the conference remaining highly competitive despite its overall growing popularity.

The evaluation of machine learning algorithms in biomedical fields for applications involving sequential data lacks standardization. Common quantitative scalar evaluation metrics such as sensitivity and specificity can often be misleading depending on the requirements of the application. Evaluation metrics must ultimately reflect the needs of users yet be sufficiently sensitive to guide algorithm development. Feedback from critical care clinicians who use automated event detection software in clinical applications has been overwhelmingly emphatic that a low false alarm rate, typically measured in units of the number of errors per 24 hours, is the single most important criterion for user acceptance. Though using a single metric is not often as insightful as examining performance over a range of operating conditions, there is a need for a single scalar figure of merit. In this paper, we discuss the deficiencies of existing metrics for a seizure detection task and propose several new metrics that offer a more balanced view of performance. We demonstrate these metrics on a seizure detection task based on the TUH EEG Corpus. We show that two promising metrics are a measure based on a concept borrowed from the spoken term detection literature, Actual Term-Weighted Value, and a new metric, Time-Aligned Event Scoring (TAES), that accounts for the temporal alignment of the hypothesis to the reference annotation. We also demonstrate that state of the art technology based on deep learning, though impressive in its performance, still needs significant improvement before it will meet very strict user acceptance guidelines.

Learning and memory are intertwined in our brain and their relationship is at the core of several recent neural network models. In particular, the Attention-Gated MEmory Tagging model (AuGMEnT) is a reinforcement learning network with an emphasis on biological plausibility of memory dynamics and learning. We find that the AuGMEnT network does not solve some hierarchical tasks, where higher-level stimuli have to be maintained over a long time, while lower-level stimuli need to be remembered and forgotten over a shorter timescale. To overcome this limitation, we introduce hybrid AuGMEnT, with leaky or short-timescale and non-leaky or long-timescale units in memory, that allow to exchange lower-level information while maintaining higher-level one, thus solving both hierarchical and distractor tasks.

Artificial intelligence (AI) generally and machine learning (ML) specifically demonstrate impressive practical success in many different application domains, e.g. in autonomous driving, speech recognition, or recommender systems. Deep learning approaches, trained on extremely large data sets or using reinforcement learning methods have even exceeded human performance in visual tasks, particularly on playing games such as Atari, or mastering the game of Go. Even in the medical domain there are remarkable results. The central problem of such models is that they are regarded as black-box models and even if we understand the underlying mathematical principles, they lack an explicit declarative knowledge representation, hence have difficulty in generating the underlying explanatory structures. This calls for systems enabling to make decisions transparent, understandable and explainable. A huge motivation for our approach are rising legal and privacy aspects. The new European General Data Protection Regulation entering into force on May 25th 2018, will make black-box approaches difficult to use in business. This does not imply a ban on automatic learning approaches or an obligation to explain everything all the time, however, there must be a possibility to make the results re-traceable on demand. In this paper we outline some of our research topics in the context of the relatively new area of explainable-AI with a focus on the application in medicine, which is a very special domain. This is due to the fact that medical professionals are working mostly with distributed heterogeneous and complex sources of data. In this paper we concentrate on three sources: images, *omics data and text. We argue that research in explainable-AI would generally help to facilitate the implementation of AI/ML in the medical domain, and specifically help to facilitate transparency and trust.

Automated seizure detection using clinical electroencephalograms is a challenging machine learning problem because the multichannel signal often has an extremely low signal to noise ratio. Events of interest such as seizures are easily confused with signal artifacts (e.g, eye movements) or benign variants (e.g., slowing). Commercially available systems suffer from unacceptably high false alarm rates. Deep learning algorithms that employ high dimensional models have not previously been effective due to the lack of big data resources. In this paper, we use the TUH EEG Seizure Corpus to evaluate a variety of hybrid deep structures including Convolutional Neural Networks and Long Short-Term Memory Networks. We introduce a novel recurrent convolutional architecture that delivers 30% sensitivity at 7 false alarms per 24 hours. We have also evaluated our system on a held-out evaluation set based on the Duke University Seizure Corpus and demonstrate that performance trends are similar to the TUH EEG Seizure Corpus. This is a significant finding because the Duke corpus was collected with different instrumentation and at different hospitals. Our work shows that deep learning architectures that integrate spatial and temporal contexts are critical to achieving state of the art performance and will enable a new generation of clinically-acceptable technology.

Objective: A clinical decision support tool that automatically interprets EEGs can reduce time to diagnosis and enhance real-time applications such as ICU monitoring. Clinicians have indicated that a sensitivity of 95% with a specificity below 5% was the minimum requirement for clinical acceptance. We propose a highperformance classification system based on principles of big data and machine learning. Methods: A hybrid machine learning system that uses hidden Markov models (HMM) for sequential decoding and deep learning networks for postprocessing is proposed. These algorithms were trained and evaluated using the TUH EEG Corpus, which is the world's largest publicly available database of clinical EEG data. Results: Our approach delivers a sensitivity above 90% while maintaining a specificity below 5%. This system detects three events of clinical interest: (1) spike and/or sharp waves, (2) periodic lateralized epileptiform discharges, (3) generalized periodic epileptiform discharges. It also detects three events used to model background noise: (1) artifacts, (2) eye movement (3) background. Conclusions: A hybrid HMM/deep learning system can deliver a low false alarm rate on EEG event detection, making automated analysis a viable option for clinicians. Significance: The TUH EEG Corpus enables application of highly data consumptive machine learning algorithms to EEG analysis. Performance is approaching clinical acceptance for real-time applications.

Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio. They pose density estimation as a sequence modeling task, where a recurrent neural network (RNN) models the conditional distribution over the next element conditioned on all previous elements. In this paradigm, the bottleneck is the extent to which the RNN can model long-range dependencies, and the most successful approaches rely on causal convolutions, which offer better access to earlier parts of the sequence than conventional RNNs. Taking inspiration from recent work in meta reinforcement learning, where dealing with long-range dependencies is also essential, we introduce a new generative model architecture that combines causal convolutions with self attention. In this note, we describe the resulting model and present state-of-the-art log-likelihood results on CIFAR-10 (2.85 bits per dim) and $32 \times 32$ ImageNet (3.80 bits per dim). Our implementation is available at https://github.com/neocxi/pixelsnail-public

Neural networks have been successfully implemented in a plethora of prediction tasks ranging from speech interpretation to facial recognition. Because of groundbreaking work in optimization techniques (such as batch normalization, Ioffe and Szegedy (2015)) and model architecture (convolutional, deep belief, and LSTM networks), it is now tractable to use deep neural networks to effectively learn a better feature representation compared to handcrafted methods. 1 One area where such methods have not been utilized is the space of adversarial multiagent systems (for example, multiple independent players in competition), specifically when the multiagent behavior comes in the form of trajectories. There are two reasons for this: i) procuring large volumes of data where deep methods are effective is difficult to obtain, and ii) forming an initial representation of the raw trajectories so that deep neural networks are effective is challenging. In this paper, we explore the effectiveness of deep neural networks on a large volume of basketball tracking data, which contains the x, y locations of multiple agents (players) in an adversarial domain (game). To thoroughly explore this problem, we focus on the following task: "given the trajectories of the players and ball in the previous five seconds, can we accurately predict the likelihood that a player with position/role X will make the shot?"

It is becoming very hard to stay up to date with recent advancements happening in deep learning. Hardly a day goes by without a new innovation or a new application of deep learning coming by. To keep ourselves updated, we have created a small reading group to share our learnings internally at Analytics Vidhya. One such learning I would like to share with the community is a a survey of advanced architectures which have been developed by the research community. This article contains some of the recent advancements in Deep Learning along with codes for implementation in keras library.

I have a confession to make. I feel like a fraud. Every few days, I receive an email from either a friend, a friend of a friend, or a random company that asks me for my insights in Artificial Intelligence. These include entrepreneurs who have just sold their startups, Stanford MBA graduates who reject half a million dollar offers, venture capitalists, even major bank executives. A couple of years earlier, I wouldn't even have the courage to approach those people, let alone dreaming about them wanting to talk to me.