Faculty

Biography: Atlas’ research has had an impact on signal processing for dynamical systems, time-frequency analysis and nonstationary statistics, with applications in streaming data, acoustics, machine monitoring, sensor arrays, speech processing and auditory sciences. His publication “Improving Generalization with Active Learning” initiated the machine learning area of active learning. His earlier work: “Training Connectionist Networks with Queries and Selective Sampling,” was the first on selective sampling, and continues to have impact in machine learning. Atlas’ graduate students have also had tremendous impact — such as the first publication on trained (linear) convolutional neural networks for temporal signals, securing top faculty positions, and initiating machine learning at Google.