Neural Network to Write Picture-Based Poems

Microsoft had created XiaoIce chatbot that is the neural network poet
13 August 2018   928

Microsoft has trained XiaoIce's artificial intelligence system to read the image and generate Chinese poems describing what is depicted on it. This is reported by The Next Web.

The system consists of two neural networks. One of them recognizes the details in the picture and selects keywords, and then generates a poem. The second part evaluates the total. The algorithm received a set of instructions from the researchers and worked until the best result was achieved. If it did not suit the researchers, they changed the instruction set and restarted the system.

For example, for such an image, the algorithm generates a poem:

Example Image for XiaoIce
Example Image for XiaoIce

Wings hold rocks and water lightly

in the loneliness

Stroll the empty

The land becomes soft

Xiaolce's Poem

According to scientists, modern Chinese poetry requires great imagination and creative use of language, which is a difficult task even for a person.

To determine the quality of the program, the researchers conducted experiments, where they offered people to choose between the poems of the Microsoft bot and other algorithms. In the overwhelming majority of participants chose the first option.

Nvidia to Open SPADE Source Code

SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019   672

NVIDIA has released the source code for the SPADE machine learning system (GauGAN), which allows for the synthesis of realistic landscapes based on rough sketches, as well as training models associated with the project. The system was demonstrated in March at the GTC 2019 conference, but the code was published only yesterday. The developments are open under the non-free license CC BY-NC-SA 4.0 (Creative Commons Attribution-NonCommercial-ShareAlike 4.0), allowing use only for non-commercial purposes. The code is written in Python using the PyTorch framework.

Sketches are drawn up in the form of a segmented map that determines the placement of exemplary objects on the scene. The nature of the generated objects is set using color labels. For example, a blue fill turns into sky, blue into water, dark green into trees, light green into grass, light brown into stones, dark brown into mountains, gray into snow, a brown line into a road, and a blue line into the river. Additionally, based on the choice of reference images, the overall style of the composition and the time of day are determined. The proposed tool for creating virtual worlds can be useful to a wide range of specialists, from architects and urban planners to game developers and landscape designers.

Objects are synthesized by a generative-adversarial neural network (GAN), which, based on a schematic segmented map, creates realistic images by borrowing parts from a model previously trained on several million photographs. In contrast to the previously developed systems of image synthesis, the proposed method is based on the use of adaptive spatial transformation followed by transformation based on machine learning. Processing a segmented map instead of semantic markup allows you to achieve an exact match of the result and control the style.

To achieve realism, two competing neural networks are used: the generator and the discriminator (Discriminator). The generator generates images based on mixing elements of real photos, and the discriminator identifies possible deviations from real images. As a result, a feedback is formed, on the basis of which the generator begins to assemble more and more qualitative samples, until the discriminator ceases to distinguish them from the real ones.