PyTorch 1.4 has been released, and the PyTorch domain libraries have been updated along with it. The popular open source machine learning framework has some experimental features on board, so let's take a closer look. PyTorch Mobile was first introduced in PyTorch 1.3 as an experimental release. It should provide an "end-to-end workflow from Python to deployment on iOS and Android," as the website states. In the latest release, PyTorch Mobile is still experimental but has received additional features.

Few industries have as much historical and structured data than the financial services industry, making it the perfect playing field for machine learning technologies. Investment banks were pioneers of AI technologies, using machine learning since as early as the 1980s. Nowadays, traders and fund managers rely on AI-driven market analysis to make investment decisions that are paving the way for fintech companies to develop new digital solutions for financial trading. AI-driven solutions such as stock-ranking based on pattern matching and deep learning for formulating investment strategies are just some of the innovations available on the market today.

Few industries have as much historical and structured data than the financial services industry, making it the perfect playing field for machine learning technologies. Investment banks were pioneers of AI technologies, using machine learning since as early as the 1980s. Nowadays, traders and fund managers rely on AI-driven market analysis to make investment decisions that are paving the way for fintech companies to develop new digital solutions for financial trading. AI-driven solutions such as stock-ranking based on pattern matching and deep learning for formulating investment strategies are just some of the innovations available on the market today.

Increasingly, machine learning forms of artificial intelligence are contending with the limits of computing hardware, and it's causing scientists to rethink how they design neural networks. That was clear in last week's research offering from Google, called Reformer, which aimed to stuff a natural language program into a single graphics processing chip instead of eight. And this week brought another offering from Google focused on efficiency, something called Sideways. With this invention, scientists have borrowed a page from computer architecture, creating a pipeline that gets more work done at every moment. Most machine learning neural nets during their training phase use a forward pass, a transmission of a signal through layers of the network, followed by backpropagation, a backward pass through the same layers, only in reverse, to gradually modify the weights of a neural network till they're just right.

We describe the design of a voice trigger detection system for smart speakers. In this study, we address two major challenges. The first is that the detectors are deployed in complex acoustic environments with external noise and loud playback by the device itself. Secondly, collecting training examples for a specific keyword or trigger phrase is challenging resulting in a scarcity of trigger phrase specific training data. We describe a two-stage cascaded architecture where a low-power detector is always running and listening for the trigger phrase. If a detection is made at this stage, the candidate audio segment is re-scored by larger, more complex models to verify that the segment contains the trigger phrase. In this study, we focus our attention on the architecture and design of these second-pass detectors. We start by training a general acoustic model that produces phonetic transcriptions given a large labelled training dataset. Next, we collect a much smaller dataset of examples that are challenging for the baseline system. We then use multi-task learning to train a model to simultaneously produce accurate phonetic transcriptions on the larger dataset \emph{and} discriminate between true and easily confusable examples using the smaller dataset. Our results demonstrate that the proposed model reduces errors by half compared to the baseline in a range of challenging test conditions \emph{without} requiring extra parameters.

Automatic speech transcription and speaker recognition are usually treated as separate tasks even though they are interdependent. In this study, we investigate training a single network to perform both tasks jointly. We train the network in a supervised multi-task learning setup, where the speech transcription branch of the network is trained to minimise a phonetic connectionist temporal classification (CTC) loss while the speaker recognition branch of the network is trained to label the input sequence with the correct label for the speaker. We present a large-scale empirical study where the model is trained using several thousand hours of labelled training data for each task. We evaluate the speech transcription branch of the network on a voice trigger detection task while the speaker recognition branch is evaluated on a speaker verification task. Results demonstrate that the network is able to encode both phonetic \emph{and} speaker information in its learnt representations while yielding accuracies at least as good as the baseline models for each task, with the same number of parameters as the independent models.

--The development of human-robot systems able to leverage the strengths of both humans and their robotic counterparts has been greatly sought after because of the foreseen, broad-ranging impact across industry and research. We believe the true potential of these systems cannot be reached unless the robot is able to act with a high level of autonomy, reducing the burden of manual tasking or teleoperation. T o achieve this level of autonomy, robots must be able to work fluidly with its human partners, inferring their needs without explicit commands. This inference requires the robot to be able to detect and classify the heterogeneity of its partners. We propose a framework for learning from heterogeneous demonstration based upon Bayesian inference and evaluate a suite of approaches on a real-world dataset of gameplay from StarCraft II. This evaluation provides evidence that our Bayesian approach can outperform conventional methods by up to 12.8 % . 1 Index T erms--Learning from Demonstration; Human-Robot Interaction; Human-Robot T eaming; Deep Learning I.

Time series forecasting has gained lots of attention recently; this is because many real-world phenomena can be modeled as time series. The massive volume of data and recent advancements in the processing power of the computers enable researchers to develop more sophisticated machine learning algorithms such as neural networks to forecast the time series data. In this paper, we propose various neural network architectures to forecast the time series data using the dynamic measurements; moreover, we introduce various architectures on how to combine static and dynamic measurements for forecasting. We also investigate the importance of performing techniques such as anomaly detection and clustering on forecasting accuracy. Our results indicate that clustering can improve the overall prediction time as well as improve the forecasting performance of the neural network. Furthermore, we show that feature-based clustering can outperform the distance-based clustering in terms of speed and efficiency. Finally, our results indicate that adding more predictors to forecast the target variable will not necessarily improve the forecasting accuracy.

Recently, the use of synthetic data generated by GANs has become a popular method to do data augmentation for many applications. While practitioners celebrate this as an economical way to obtain synthetic data for training data-hungry machine learning models, it is not clear that they recognize the perils of such an augmentation technique when applied to an already-biased dataset. Although one expects GANs to replicate the distribution of the original data, in real-world settings with limited data and finite network capacity, GANs suffer from mode collapse. Especially when this data is coming from online social media platforms or the web which are never balanced. In this paper, we show that in settings where data exhibits bias along some axes (eg. More often than not, this bias is unavoidable; we empirically demonstrate that given input of a dataset of headshots of engineering faculty collected from 47 online university directory webpages in the United States is biased toward white males, a state-of-the-art (unconditional variant of) GAN "imagines" faces of synthetic engineering professors that have masculine facial features and white skin color (inferred using human studies and a state-of- the-art gender recognition system). We also conduct a preliminary case study to highlight how Snapchat's explosively popular "female" filter (widely accepted to use a conditional variant of GAN), ends up consistently lightening the skin tones in women of color when trying to make face images appear more feminine. Our study is meant to serve as a cautionary tale for the lay practitioners who may unknowingly increase the bias in their training data by using GAN-based augmentation techniques with web data and to showcase the dangers of using biased datasets for facial applications. Introduction Breakthroughs in deep learning for image recognition have heralded significant progress in the field of computer vision, but one of the greatest limitations of the technology still remains: classifiers require massive amounts of training data to recognize meaningful patterns. As practitioners struggle to coax classifiers into generalizing to the underlying real-world distribution instead of overfitting to the sparse data, several data augmentation techniques have emerged as a useful form of regularization to increase training sample size and thereby, accuracy during test-time. The simplest of these augmentation techniques perform affine transformations on existing samples in the data, such as rotation, zooming, translation etc. (O'Gorman and Kasturi 1995; Bloice, Stocker, and Holzinger 2017). Ideally, the transformed samples should be representative of the same real-world distribution p dataas the original train and test sets.

The Ideal Observer (IO) performance has been advocated when optimizing medical imaging systems for signal detection tasks. However, analytical computation of the IO test statistic is generally intractable. To approximate the IO test statistic, sampling-based methods that employ Markov-Chain Monte Carlo (MCMC) techniques have been developed. However, current applications of MCMC techniques have been limited to several object models such as a lumpy object model and a binary texture model, and it remains unclear how MCMC methods can be implemented with other more sophisticated object models. Deep learning methods that employ generative adversarial networks (GANs) hold great promise to learn stochastic object models (SOMs) from image data. In this study, we described a method to approximate the IO by applying MCMC techniques to SOMs learned by use of GANs. The proposed method can be employed with arbitrary object models that can be learned by use of GANs, thereby the domain of applicability of MCMC techniques for approximating the IO performance is extended. In this study, both signal-known-exactly (SKE) and signal-known-statistically (SKS) binary signal detection tasks are considered. The IO performance computed by the proposed method is compared to that computed by the conventional MCMC method. The advantages of the proposed method are discussed.