The advent of deep learning has substantially accelerated machine learning development during the last decade impacting computer vision, natural language processing, and other domains. However, those deep learning implementations require almost two orders of magnitude more power compared to the human brain, requiring thus constant connection to dedicated data centers. With new memories available, emerging Binarized Neural Networks (BNNs) are promising to reduce the energy impact of the forthcoming machine learning hardware generation, enabling machine learning on the edge devices and avoiding data transfer over the network. In the talk we will discuss strategies to apply BNNs to biomedical signals such as electrocardiography and electroencephalography, without sacrificing accuracy and improving energy use. The ultimate goal of this research is to enable smart autonomous healthcare devices.