-
EMC+SIPI 20192019Unintended Electromagnetic interference (EMI) is a common occurrence in all consumer electronics, which can often fail compliance margins of FCC and/or CE, when best practices of grounding, shielding and overall system integration are not followed. The measurement of EMI for regulatory compliance has been studied extensively and there are standard test labs which certifies for EMI. However, predicting the
-
ICCV 20192019We propose a novel approach for estimating the difficulty and transferability of supervised classification tasks. Unlike previous work, our approach is solution agnostic and does not require or assume trained models. Instead, we estimate these values using an information-theoretic approach: treating training labels as random variables and exploring their statistics. When transferring from a source to a target
-
KDD AdKDD 20192019We apply and extend recent results in feasible arm identification to quickly find a small set of bidding strategies that can simultaneously meet multiple business objectives. We formulate this as an any-m feasible arm identification problem, a pure exploration multi-armed bandit problem where each arm is a D-dimensional distribution represented by a mean vector. The goal is to identify m feasible arms,meaning
-
NeurIPS 20192019Motivated by the many real-world applications of reinforcement learning (RL) that require safe-policy iterations, we consider the problem of off-policy evaluation (OPE) — the problem of evaluating a new policy using the historical data obtained by different behavior policies — under the model of nonstationary episodic Markov Decision Processes with a long horizon and large action space. Existing importance
-
NeurIPS 2019 Workshop on Conversational AI2019Training dialog policies for speech-based virtual assistants requires a plethora of conversational data. The data collection phase is often expensive and time consuming due to human involvement. To address this issue, a common solution is to build user simulators for data generation. For the successful deployment of the trained policies into real world domains, it is vital that the user simulator mimics
Related content
-
March 21, 2019Sentiment analysis is the attempt, computationally, to determine from someone’s words how he or she feels about something. It has a host of applications, in market research, media analysis, customer service, and product recommendation, among other things. Sentiment classifiers are typically machine learning systems, and any given application of sentiment analysis may suffer from a lack of annotated data for training purposes. -
March 20, 2019Although deep neural networks have enabled accurate large-vocabulary speech recognition, training them requires thousands of hours of transcribed data, which is time-consuming and expensive to collect. So Amazon scientists have been investigating techniques that will let Alexa learn with minimal human involvement, techniques that fall in the categories of unsupervised and semi-supervised learning.
-
March 11, 2019In experiments involving sound recognition, technique reduces error rate by 15% to 30%.
-
March 5, 2019The 2018 Alexa Prize featured eight student teams from four countries, each of which adopted distinctive approaches to some of the central technical questions in conversational AI. We survey those approaches in a paper we released late last year, and the teams themselves go into even greater detail in the papers they submitted to the latest Alexa Prize Proceedings. Here, we touch on just a few of the teams’ innovations.
-
February 27, 2019To ensure that Alexa Prize contestants can concentrate on dialogue systems — the core technology of socialbots — Amazon scientists and engineers built a set of machine learning modules that handle fundamental conversational tasks and a development environment that lets contestants easily mix and match existing modules with those of their own design.
-
January 30, 2019Many of today’s most popular AI systems are, at their core, classifiers. They classify inputs into different categories: this image is a picture of a dog, not a cat; this audio signal is an instance of the word “Boston”, not the word “Seattle”; this sentence is a request to play a video, not a song. But what happens if you need to add a new class to your classifier — if, say, someone releases a new type of automated household appliance that your smart-home system needs to be able to control?
