Deep learning algorithms are emerging as powerful alternatives to compressed sensing methods, offering improved image quality and computational efficiency. Fully sampled training images are often difficult to acquire in high-resolution and dynamic imaging applications. We propose an ENsemble SURE (ENSURE) loss metric to train a deep network only from undersampled measurements. In particular, we show that training a network using an ensemble of images, each acquired with a different sampling pattern, using ENSURE can provide results that closely approach MSE training. Our experimental results show comparable reconstruction quality to supervised learning.