Abstract: In some embodiments, techniques are provided for analyzing time series data to detect anomalies. In some embodiments, the time series data is processed using a machine learning model. In some embodiments, the machine learning model is trained in an unsupervised manner on large amounts of previous time series data, thus allowing highly accurate models to be created from novel data. In some embodiments, training of the machine learning model alternates between a fitting optimization and a trimming optimization to allow large amounts of training data that includes untagged anomalous records to be processed. Because a machine learning model is used, anomalies can be detected within complex systems, including but not limited to autonomous vehicles such as unmanned aerial vehicles. When anomalies are detected, commands can be transmitted to the monitored system (such as an autonomous vehicle) to respond to the anomaly.

Abstract: In some embodiments, techniques are provided for analyzing time series data to detect anomalies. In some embodiments, the time series data is processed using a machine learning model. In some embodiments, the machine learning model is trained in an unsupervised manner on large amounts of previous time series data, thus allowing highly accurate models to be created from novel data. In some embodiments, training of the machine learning model alternates between a fitting optimization and a trimming optimization to allow large amounts of training data that includes untagged anomalous records to be processed. Because a machine learning model is used, anomalies can be detected within complex systems, including but not limited to autonomous vehicles such as unmanned aerial vehicles. When anomalies are detected, commands can be transmitted to the monitored system (such as an autonomous vehicle) to respond to the anomaly.

Abstract: A computer-implemented method includes receiving a sequence of acoustic frames as input to an automatic speech recognition (ASR) model. Here, the ASR model includes a causal encoder and a decoder. The method also includes generating, by the causal encoder, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The method also includes generating, by the decoder, a first probability distribution over possible speech recognition hypotheses. Here, the causal encoder includes a stack of causal encoder layers each including a Recurrent Neural Network (RNN) Attention-Performer module that applies linear attention.

Abstract: The present disclosure provides iterative blackbox optimization techniques that estimate the gradient of a function. According to an aspect of the present disclosure, a plurality of perturbations used at each iteration can be sampled from a non-orthogonal sampling distribution. As one example, in some implementations, perturbations that have been previously evaluated in previous iterations can be re-used at the current iteration. thereby conserving computing resources because the re-used perturbations do not need to be re-evaluated at the current iteration. In another example, in addition or alternatively to the use of previously evaluated perturbations, the perturbations evaluated at the current iteration can be sampled from a non-orthogonal sampling distribution.

Abstract: In some embodiments, techniques are provided for analyzing time series data to detect anomalies. In some embodiments, the time series data is processed using a machine learning model. In some embodiments, the machine learning model is trained in an unsupervised manner on large amounts of previous time series data, thus allowing highly accurate models to be created from novel data. In some embodiments, training of the machine learning model alternates between a fitting optimization and a trimming optimization to allow large amounts of training data that includes untagged anomalous records to be processed. Because a machine learning model is used, anomalies can be detected within complex systems, including but not limited to autonomous vehicles such as unmanned aerial vehicles. When anomalies are detected, commands can be transmitted to the monitored system (such as an autonomous vehicle) to respond to the anomaly.