Abstract: Apparatuses, systems, and techniques are presented to train and utilize one or more neural networks. A denoising diffusion generative adversarial network (denoising diffusion GAN) reduces a number of denoising steps during a reverse process. The denoising diffusion GAN does not assume a Gaussian distribution for large steps of the denoising process and applies a multi-model model to permit denoising with fewer steps. Systems and methods further minimize a divergence between a diffused real data distribution and a diffused generator distribution over several timesteps. Accordingly, various embodiments may enable faster sample generation, in which the samples are generated from noise using the denoising diffusion GAN.

Abstract: The invention provides a fluorinated chitosan derivative as a drug carrier, which has the following structure: a fluorine-containing compound covalently attached to the backbone of chitosan. The chitosan has a molecular weight in the range of 1000-5000000, a degree of deacetylation of not less than 55%, and a viscosity in the range of 25-1000 cps. The fluorine-containing compound is a fluorine-containing aliphatic chain shown by the following chemical formula (I) or an aromatic ring with functional groups shown by the following formula (II) wherein R1 is halogen (fluorine, chlorine, bromine, iodine), or a halogen-substituted alkane, cycloalkane, aldehyde group, carboxyl group, alkenyl group, alkynyl group, hydroxyl group, sulfonyl chloride, sulfonic acid bond or mercapto group, for interacting with a primary amino group. The compounds of the present invention can be universally bound to a variety of drugs to promote drug absorption and bioavailability, and reduce toxicity.

Abstract: One embodiment sets forth a technique for creating a generative model. The technique includes generating a trained generative model with a first component that converts data points in the training dataset into latent variable values, a second component that learns a distribution of the latent variable values, and a third component that converts the latent variable values into output distributions. The technique also includes training an energy-based model to learn an energy function based on values sampled from a first distribution associated with the training dataset and values sampled from a second distribution during operation of the trained generative model. The technique further includes creating a joint model that includes one or more portions of the trained generative model and the energy-based model, and that applies energy values from the energy-based model to samples from the second distribution to produce additional values used to generate a new data point.

Abstract: One embodiment of the present invention sets forth a technique for generating data using a generative model. The technique includes sampling from one or more distributions of one or more variables to generate a first set of values for the one or more variables, where the one or more distributions are used during operation of one or more portions of the generative model. The technique also includes applying one or more energy values generated via an energy-based model to the first set of values to produce a second set of values for the one or more variables. The technique further includes either outputting the set of second values as output data or performing one or more operations based on the second set of values to generate output data.