Neural Network to Write Picture-Based Poems

Microsoft had created XiaoIce chatbot that is the neural network poet
13 August 2018   1268

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.

TensorFlow 2.0 to be Released

New major release of the machine learning platform brought a lot of updates and changes, some stuff even got cut
01 October 2019   172

A significant release of the TensorFlow 2.0 machine learning platform is presented, which provides ready-made implementations of various deep machine learning algorithms, a simple programming interface for building models in Python, and a low-level interface for C ++ that allows you to control the construction and execution of computational graphs. The system code is written in C ++ and Python and is distributed under the Apache license.

The platform was originally developed by the Google Brain team and is used in Google services for speech recognition, facial recognition in photographs, determining the similarity of images, filtering spam in Gmail, selecting news in Google News and organizing the translation taking into account the meaning. Distributed machine learning systems can be created on standard equipment, thanks to the built-in support in TensorFlow for spreading computing to multiple CPUs or GPUs.

TensorFlow provides a library of off-the-shelf numerical computation algorithms implemented through data flow graphs. The nodes in such graphs implement mathematical operations or entry / exit points, while the edges of the graph represent multidimensional data arrays (tensors) that flow between the nodes. The nodes can be assigned to computing devices and run asynchronously, simultaneously processing all the suitable tensors at the same time, which allows you to organize the simultaneous operation of nodes in the neural network by analogy with the simultaneous activation of neurons in the brain.

Get more info about the update at official website.