A keyword spotting (KWS) engine that is continuously running on device is exposed to various speech signals that are usually unseen before. It is a challenging problem to build a small-footprint and high-performing KWS model with robustness under different acoustic environments. In this paper, we explore how to effectively apply adversarial examples to improve KWS robustness. We propose datasource-aware disentangled learning with adversarial examples to reduce the mismatch between the original and adversarial data as well as the mismatch across original training datasources. The KWS model architecture is based on depth-wise separable convolution and a simple attention module. Experimental results demonstrate that the proposed learning strategy improves false reject rate by $40.31%$ at $1%$ false accept rate on the internal dataset, compared to the strongest baseline without using adversarial examples. Our best-performing system achieves $98.06%$ accuracy on the Google Speech Commands V1 dataset.

This is to use Camera's camera view. Changing the width and height, 1280 x 720 worked great for me, but you can play around with the dimensions to see what fits your need. I set this to 30, the higher you set the number the more computing power it would require. You can play around to see what the benchmark for it, but 30 has worked great for me.

Is it possible to distinguish one class of samples from another, based on some set of measurements? Research investigating this and related medical questions have spurred innovation in medicine and the application of statistical methods and machine learning for decades. In this post, we'll address how to answer these questions using highly available, scalable, and easy-to-use cloud computing services that are included in Amazon Web Services (AWS). We'll start by guiding you through using Amazon Machine Learning to classify medical tumor samples as benign or malignant. Then, we'll explore other machine learning services and how they could be used to investigate medical questions.

I first came across a real application of Machine Learning at work. We were supposed to prepare an application that will recognize frauds in the Zooplus shop. After months of trying different solutions: external providers, additional if statements in the code, fire-fighting scripts and such, we ended up with a conclusion that Machine Learning is the best tool for the job. Since then, we were trying to convince everyone around to invest in our education and pursue the Machine Learning path, but without any spectacular successes. Yet I had a chance to make my first step by playing a bit with Amazon's Machine Learning capabilities, so I consider myself a level 2 dummy.

Air travel can be stressful due to the many factors that are simply out of airline passengers' control. As passengers, we want to minimize this stress as much as we can. We can do this by using past data to make predictions about how likely a flight will be delayed based on the time of day or the airline carrier. In this post, we generate a predictive model for flight delays that can be used to help us pick the flight least likely to add to our travel stress. To accomplish this, we will use Apache Spark running on Amazon EMR for extracting, transforming, and loading (ETL) the data, Amazon Redshift for analysis, and Amazon Machine Learning for creating predictive models.

With Amazon Machine Learning (Amazon ML), you can build and train predictive models and host your applications in a scalable cloud solution. In this project, you will use the visualization tools and wizards of Amazon ML to guide you through the process of creating a new machine learning (ML) model without having to learn complex ML algorithms and technology. To complete this project, you will download freely-available sample customer data and upload the data to an Amazon S3 bucket to create a datasource. You will then create an ML model from this datasource, from which you can then evaluate and adjust the ML model's performance, and then use it to generate predictions.

The semantic layer is the underpinning of modern business intelligence platforms. The real number might be closer to 60% or even higher. It was pioneered by Business Objects in the early 90's well before the acquisition by SAP and they still remain the market leader in BI after all these years. Back to the original question - what is the semantic layer exactly? Close, but I think thats too high level and simplistic.