This week I worked on Homework 1: Imitation Learning from the Fall 2017 CS294 course at Berkeley. Professor Levine is an amazing lecturer and the information he covers in one lecture is quite dense.
Imitation Learning is a form of Supervised machine learning for behavior. For this exercise, we were supplied with expert policies for six different OpenAI Gym Mujoco environments. Each environment has different observation and action spaces:
This week I learned about the Reinforcement Learning algorithms called Monte Carlo (MC) methods. Most of my instruction came from Chapter 5 of Reinforcement Learning: An Introduction by Sutton and Barto.
I’m happy to be a member of the inaugural group of OpenAI Scholars. Every Friday for the next three months, I'll be writing a blog post about my Machine Learning studies, struggles, and successes.
Using WaveNet, a deep neural network, I was able to synthesize a ten second clip of Sylvia Plath's voice. WaveNet was trained without text sequences, so the generated speech is gibberish:
The network was trained on 1000+ audio clips from 80 minutes of poetry spoken by Sylvia Plath. Here is an example of one of the clips:
Acrylic painting can be more eco-friendly than oil painting, but the chemical composition of pigments and binders should be investigated by all artists before purchasing paints. Some pigments can be toxic and others may contain heavy metals that should not be washed down the drain.
Start by reading the labels on each paint tube. In addition, the material safety data sheet (MSDS) [1] for your acrylic paint line can be helpful.
Here are the guidelines I use for Golden's acrylic line:
When creating your artist's statement. Read two types of art writing:
Not all artists are successful at articulating and theorizing about their art. See Picasso's essay on African work or Cindy Sherman's statements from the 80s.