Investment decisions can benefit from incorporating an accumulated knowledge of the past to drive future decision making. We introduce Continual Learning Augmentation (CLA) which is based on an explicit memory structure and a feed forward neural network (FFNN) base model and used to drive long term financial investment decisions. We demonstrate that our approach improves accuracy in investment decision making while memory is addressed in an explainable way. Our approach introduces novel remember cues, consisting of empirically learned change points in the absolute error series of the FFNN. Memory recall is also novel, with contextual similarity assessed over time by sampling distances using dynamic time warping (DTW). We demonstrate the benefits of our approach by using it in an expected return forecasting task to drive investment decisions. In an investment simulation in a broad international equity universe between 2003-2017, our approach significantly outperforms FFNN base models. We also illustrate how CLA's memory addressing works in practice, using a worked example to demonstrate the explainability of our approach.

Google Assistant hasn't been traveling, but it has picked up some new accents. The voice assistant now has the ability to speak in an Australian or English accent (though Google calls it British). The feature is available across all devices including Android phones and Google Home speakers, but only for English speakers in the US for the time being. In order to produce the accents in an accurate way, Google is tapping into the artificial intelligence of DeepMind. Google Assistant uses WaveNet, the AI company's speech synthesis model powered by deep neural networks, to generate natural sounding voices.

Ranking score levels and functional categories are as in the key in (B). Highlighted ranks and terms correspond to examples shown in (D).

Achieving high catalytic performance with the lowest possible amount of platinum is critical for fuel cell cost reduction. Here we describe a method of preparing highly active yet stable electrocatalysts containing ultralow-loading platinum content by using cobalt or bimetallic cobalt and zinc zeolitic imidazolate frameworks as precursors. Synergistic catalysis between strained platinum-cobalt core-shell nanoparticles over a platinum-group metal (PGM)–free catalytic substrate led to excellent fuel cell performance under 1 atmosphere of O2 or air at both high-voltage and high-current domains. Two catalysts achieved oxygen reduction reaction (ORR) mass activities of 1.08 amperes per milligram of platinum (A mgPt 1) and 1.77 A mgPt 1 and retained 64% and 15% of initial values after 30,000 voltage cycles in a fuel cell.

David Duvenaud was working on a project involving medical data when he hit upon a major shortcoming in AI. An AI researcher at the University of Toronto, he wanted to build a deep-learning model that would predict a patient's health over time. But data from medical records is kind of messy: throughout your life, you might visit the doctor at different times for different reasons, generating a smattering of measurements at arbitrary intervals. A traditional neural network struggles to handle this. Its design requires it to learn from data with clear stages of observation.

ABSTRACT Representation learning is an essential problem in a wide range of applications and it is important for performing downstream tasks successfully. In this paper, we propose a new model that learns coupled representations of domains, intents, and slots by taking advantage of their hierarchical dependency in a Spoken Language Understanding system. Our proposed model learns the vector representation of intents based on the slots tied to these intents by aggregating the representations of the slots. Similarly, the vector representation of a domain is learned by aggregating the representations of the intents tied to a specific domain. To the best of our knowledge, it is the first approach to jointly learning the representations of domains, intents, and slots using their hierarchical relationships. The experimental results demonstrate the effectiveness of the representations learned by our model, as evidenced by improved performance on the contextual cross-domain reranking task.

Fourier methods have a long and proven track record in as an excellent tool in data processing. We propose to integrate Fourier methods into complex recurrent neural network architectures and show accuracy improvements on analysis and prediction tasks as well as computational load reductions. We predict synthetic data drawn from the synthetic-Lorenz equations as well as real world human motion prediction. We demonstrate the setup's analysis capabilities on the task of music recognition.

As societies around the world are ageing, the number of Alzheimer's disease (AD) patients is rapidly increasing. To date, no low-cost, non-invasive biomarkers have been established to advance the objectivization of AD diagnosis and progression assessment. Here, we utilize Bayesian neural networks to develop a multivariate predictor for AD severity using a wide range of quantitative EEG (QEEG) markers. The Bayesian treatment of neural networks both automatically controls model complexity and provides a predictive distribution over the target function, giving uncertainty bounds for our regression task. It is therefore well suited to clinical neuroscience, where data sets are typically sparse and practitioners require a precise assessment of the predictive uncertainty. We use data of one of the largest prospective AD EEG trials ever conducted to demonstrate the potential of Bayesian deep learning in this domain, while comparing two distinct Bayesian neural network approaches, i.e., Monte Carlo dropout and Hamiltonian Monte Carlo.

The shape of an object is an important characteristic for many vision problems such as segmentation, detection and tracking. Being independent of appearance, it is possible to generalize to a large range of objects from only small amounts of data. However, shapes represented as silhouette images are challenging to model due to complicated likelihood functions leading to intractable posteriors. In this paper we present a generative model of shapes which provides a low dimensional latent encoding which importantly resides on a smooth manifold with respect to the silhouette images. The proposed model propagates uncertainty in a principled manner allowing it to learn from small amounts of data and providing predictions with associated uncertainty. We provide experiments that show how our proposed model provides favorable quantitative results compared with the state-of-the-art while simultaneously providing a representation that resides on a low-dimensional interpretable manifold.

For the last few years it has been observed that the Deep Neural Networks (DNNs) has achieved an excellent success in image classification, speech recognition. But DNNs are suffer great deal of challenges for time series forecasting because most of the time series data are nonlinear in nature and highly dynamic in behaviour. The time series forecasting has a great impact on our socio-economic environment. Hence, to deal with these challenges its need to be redefined the DNN model and keeping this in mind, data pre-processing, network architecture and network parameters are need to be consider before feeding the data into DNN models. Data normalization is the basic data pre-processing technique form which learning is to be done. The effectiveness of time series forecasting is heavily depend on the data normalization technique. In this paper, different normalization methods are used on time series data before feeding the data into the DNN model and we try to find out the impact of each normalization technique on DNN to forecast the time series. Here the Deep Recurrent Neural Network (DRNN) is used to predict the closing index of Bombay Stock Exchange (BSE) and New York Stock Exchange (NYSE) by using BSE and NYSE time series data.