We investigate the incorporation of visual relationships into the task of supervised image caption generation by proposing a model that leverages detected objects and auto-generated visual relationships to describe images in natural language.
Computer-aided drug discovery is an essential component of modern drug development.
Convolutional networks are successful due to their equivariance/invariance under translations.
Here we show that learning to evolve, i. e. learning to mutate and recombine better than at random, improves the result of evolution in terms of fitness increase per generation and even in terms of attainable fitness.
Since abnormal samples are not used during training, we define novelty metrics based on the (partially complementary) assumptions that the VAE is less capable of reconstructing abnormal samples well; that abnormal samples more strongly violate the VAE regularizer; and that abnormal samples differ from normal samples not only in input-feature space, but also in the VAE latent space and VAE output.
Regularization is one of the crucial ingredients of deep learning, yet the term regularization has various definitions, and regularization methods are often studied separately from each other.
In this paper, we show that deep learning can predict biological function of molecules directly from their raw 3D approximated electron density and electrostatic potential fields.
A contact map is a compact representation of the three-dimensional structure of a protein via the pairwise contacts between the amino acid constituting the protein.
Optical flow estimation has not been among the tasks where CNNs were successful.