DELIMIT is a framework extension for deep learning in diffusion imaging, which extends the basic framework PyTorch towards spherical signals. Based on several novel layers, deep learning can be applied to spherical diffusion imaging data in a very convenient way. First, two spherical harmonic interpolation layers are added to the extension, which allow to transform the signal from spherical surface space into the spherical harmonic space, and vice versa. In addition, a local spherical convolution layer is introduced that adds the possibility to include gradient neighborhood information within the network. Furthermore, these extensions can also be utilized for the preprocessing of diffusion signals.

LSTMs and GRUs are the most common recurrent neural network architectures used to solve temporal sequence problems. The two architectures have differing data flows dealing with a common component called the cell state also referred to as the memory. We attempt to enhance the memory by presenting a biologically inspired modification that we call the Mother Compact Recurrent Memory MCRM. MCRMs are a type of a nested LSTM-GRU architecture where the cell state is the GRU's hidden state. The relationship between the womb and the fetus is analogous to the relationship between the LSTM and GRU inside MCRM in that the fetus is connected to its womb through the umbilical cord. The umbilical cord consists of two arteries and one vein. The two arteries are considered as an input to the fetus which is analogous to the concatenation of the forget gate and input gate from the LSTM. The vein is the output from the fetus which plays the role of the hidden state of the GRU. Because MCRMs has this type of nesting, MCRMs have a compact memory pattern consisting of neurons that act explicitly in both long-term and short-term fashions. For some specific tasks, empirical results show that MCRMs outperform previously used architectures.

In automatic speech processing systems, speaker diarization is a crucial front-end component to separate segments from different speakers. Inspired by the recent success of deep neural networks (DNNs) in semantic inferencing, triplet loss-based architectures have been successfully used for this problem. However, existing work utilizes conventional i-vectors as the input representation and builds simple fully connected networks for metric learning, thus not fully leveraging the modeling power of DNN architectures. This paper investigates the importance of learning effective representations from the sequences directly in metric learning pipelines for speaker diarization. More specifically, we propose to employ attention models to learn embeddings and the metric jointly in an end-to-end fashion. Experiments are conducted on the CALLHOME conversational speech corpus. The diarization results demonstrate that, besides providing a unified model, the proposed approach achieves improved performance when compared against existing approaches.

This paper describes how the "SP Theory of Intelligence" with the "SP Computer Model", outlined in an Appendix, may throw light on aspects of commonsense reasoning (CSR) and commonsense knowledge (CSK), as discussed in another paper by Ernest Davis and Gary Marcus (DM). In four main sections, the paper describes: 1) The main problems to be solved; 2) Other research on CSR and CSK; 3) Why the SP system may prove useful with CSR and CSK 4) How examples described by DM may be modelled in the SP system. With regard to successes in the automation of CSR described by DM, the SP system's strengths in simplification and integration may promote seamless integration across these areas, and seamless integration of those area with other aspects of intelligence. In considering challenges in the automation of CSR described by DM, the paper describes in detail, with examples of SP-multiple-alignments. how the SP system may model processes of interpretation and reasoning arising from the horse's head scene in "The Godfather" film. A solution is presented to the 'long tail' problem described by DM. The SP system has some potentially useful things to say about several of DM's objectives for research in CSR and CSK.

In recent years there has been a sharp rise in networking applications, in which significant events need to be classified but only a few training instances are available. These are known as cases of one-shot learning. Examples include analyzing network traffic under zero-day attacks, and computer vision tasks by sensor networks deployed in the field. To handle this challenging task, organizations often use human analysts to classify events under high uncertainty. Existing algorithms use a threshold-based mechanism to decide whether to classify an object automatically or send it to an analyst for deeper inspection. However, this approach leads to a significant waste of resources since it does not take the practical temporal constraints of system resources into account. Our contribution is threefold. First, we develop a novel Deep Reinforcement One-shot Learning (DeROL) framework to address this challenge. The basic idea of the DeROL algorithm is to train a deep-Q network to obtain a policy which is oblivious to the unseen classes in the testing data. Then, in real-time, DeROL maps the current state of the one-shot learning process to operational actions based on the trained deep-Q network, to maximize the objective function. Second, we develop the first open-source software for practical artificially intelligent one-shot classification systems with limited resources for the benefit of researchers in related fields. Third, we present an extensive experimental study using the OMNIGLOT dataset for computer vision tasks and the UNSW-NB15 dataset for intrusion detection tasks that demonstrates the versatility and efficiency of the DeROL framework.

Why are the results of the latest models so difficult to reproduce? Why is the code that worked fine last year not compatible with the latest release of my deep learning framework? Why is a baseline benchmark meant to be straightforward so difficult to set up? In today's world, these are the challenges faced by Natural Language Processing (NLP) researchers. Let's take the case of a hypothetical PhD student.

Muggles and fans alike would be so excited to celebrate Harry Potter's birthday, July 31st, by reading a new Harry Potter chapter that was written strictly by artificial intelligence; it isn't per the new book – Harry Potter and the cursed child, nor is it an addition to the seventh in the series. While the muggle world will go crazy today, and the Internet may likely break due to the new Harry Potter release, we thought it would be a great added birthday gift to have a new chapter that fits after the fourth book, Harry Potter and the Goblet of Fire. So here is a little info on this new artificial intelligence Harry Potter chapter, which even JK Rowling couldn't have written: I trained an LSTM Recurrent Neural Network (a deep learning algorithm) on the first four Harry Potter books. I then asked it to produce a chapter based on what it learned. Don't expect this new machine created Harry Potter text to reveal untold secrets, a vision into the future, or what is planned for the wizarding world.

If you have been keeping up with the advancements in the area of object detection, you might have got used to hearing this word'YOLO'. It has kind of become a buzzword. YOLO (You Only Look Once) is a method / way to do object detection. It is the algorithm /strategy behind how the code is going to detect objects in the image. The official implementation of this idea is available through DarkNet (neural net implementation from the ground up in'C' from the author).

Artificial intelligence (AI) is rapidly spreading throughout the realm of medtech as companies from every corner of the market look to adapt to the latest in innovation. Whether you're an industry giant, or a shiny new startup, advancements in AI technologies are forcing companies to embrace and adapt to new developments--all while altering the medtech landscape in the process. How are companies beginning to tap their potential, and when will we begin to actually see the impact they can have on the world of healthcare? These are some of the questions that Gioel Molinari will be addressing at next month's MD&M East 2018 conference in New York, where he'll be part of a panel discussion on the topic of "How Artificial Intelligence is Moving the Needle in Medtech." Molinari is the current president of Butterfly Network Inc., a cutting-edge technology company that focuses on semiconductor technologies, cloud platforms, and artificial intelligence and deep learning technologies that can shape next-gen devices.

Dez Blanchfield speaks with business leaders about artificial intelligence and deep learning adoption in the "From Here to AI" podcast series from IBM Power Systems. When you start to investigate artificial intelligence (AI), or branch out to buy a couple AI servers to tinker with for your organization, the process of implementing a full AI solution can seem daunting. With the help of four business executives and AI leaders and digital transformation expert and avid podcaster Dez Blanchfield, we set out to outline the natural progression of implementing AI in the data center. No matter what stage of the journey you are on, these podcasts should help you get "from here to AI." Below is a quick overview of each session. We've posted them as a series so you can binge-listen if you have the time, or you can tee them up separately to plug into the ones that interest you most.