AI and Algorithmic Art - Could computer take over human creativity?

Some think neural networks are magic boxes, let the computers to have a mind of its own. Beside making classifications and predictions, neural networks have also been used to creating pictures, music, jokes and plays. Can creativity, what seems to make us special, be achieved by these magic boxes?

Algorithmic Art, which can be loosely defined as computer-generated art based on algorithms devised by the artist. Started as early as the 1960s, artists use a plotter controlled by a computer to create some artwork. Then around the late 80s, since computer graphics became more accessible, digital fractal artworks dominated to be the mainstream of algorithmic art. By the end of the 80s, the genetic algorithm was matured and was having a big role in the algorithmic composition of music. At the same time, the artificial neural networks were also put in used to generate music.

Most recently, thanks for the blooming of neural network framework in Python (e.g. TensorFlow, PyTorch), availability of GPUs and development in sophisticated neural network architecture, the neural network plays an important part in academic research and data science business applications. Besides that, computers are also given the power to be more creative in generating Algorithmic Art using neural networks. First the Deep Dream and artistic style transfer, then GAN (generative adversarial network) which can generate highly deceptive pictures. A specially trained neural network is also capable of composing music mimicking the style of Beethoven or generating a modern music piece. The list of application does not stop there, generating poems, jokes, plays, novels……

In this talk, we will go through a gallery of art and music created by algorithms, showcasing what roles computers took in different algorithmic art forms. From the earliest fractal art to the music and pictures generated by the state of the art neural networks and GANs. This talk is suitable for everyone, from curious general public to expert in neural networks, both will find this talk inspiring and amusing.