Topic

Andrea Bejarano-Carbo

Affiliation

University of Michigan, Ann Arbor, MI

Topic

Energy Efficiency,Change Detection,Convolutional Neural Network,Deep Neural Network,Energy Consumption,Neural Network,Power Consumption,Accuracy-latency Trade-off,Arbitrary Region,Artificial Neural Network,Audio Interface,Backpropagation Through Time,Balanced Trade-off,Bidirectional Recurrent Neural Network,Bit Error Rate,Carrier Frequency,Carrier Phase,Challenging Dataset,Comparable Accuracy,Compression Ratio,Computation Energy,Computational Complexity,Constant Factor,Convolutional Layers,Cost Reduction,Datapath,Dataset Statistics,Deconvolution,Depthwise Convolution,Discrete Cosine Transform,Dynamic Datasets,Dynamic Power,Dynamic Power Consumption,Dynamic Vision Sensor,Energy System,Entropy Coding,Feature Maps,Final Layer,Firing Threshold,Forward Error Correction,Frequency Drift,Frequency Noise,Frequency Values,Fully-connected Layer,Gated Recurrent Unit,Generative Adversarial Networks,Hidden Layer Output,High Compression Ratio,Image Classification,Image Compression,

Biography

Andrea Bejarano-Carbo (Graduate Student Member, IEEE) received the M.Eng. degree in electrical and electronic engineering from the University of Bristol, Bristol, U.K., in 2019, and the M.Sc. degree in electrical and computer engineering from the University of Michigan, Ann Arbor, MI, USA, in 2022, where she is currently pursuing the Ph.D. degree.
Her research interests lie in low-power and area-constrained intelligent devices for Internet-of-Things applications.
Ms. Bejarano-Carbo was a recipient of the Best Paper Award at the 2022 tinyML Research Symposium.