This week we’re bringing your new reading (and watching!) on neural networks, artificial intelligence, and…poetry. (Yes, poetry!) Check out our recommendations and share your perspectives on them in the comments.
Are you a stereotypical millennial who’s curious about many things and loves your information fast, fun, and to the point? Are you also interested in learning about machine learning, neural networks, and other cool stuff? You aren’t, but you know such a person? Make sure to check the Siraj Raval’s YouTube channel. Siraj is a Pythonista, a machine learning geek, a rapper, and, apparently, a YouTube star. He’s talking about self-driving cars, stock exchange prediction, image classification, and other cool stuff in terms that do not require deep prior knowledge.
“The dark side of data science” discusses the problems around relying too heavily on learning algorithms. The problems described in this post lie on the interface between technology and ethics. One example of such a problem is “a person denied a loan by a faulty risk model is more likely to be denied again when he or she applies elsewhere, simply because it is on their record that they have been refused credit before.”
Speaking of ethical problems, you should also read this post by Antonio Garcia-Martinez, an ex-Facebook data scientist whose main claim, that “the social media giant could target ads at depressed teens and countless other demographics. But so what?” is both bold and controversial.
I’ve been a big fan of Good Math/Bad Math for a number of years. He’s recently posted about neural networks, which is something that I’ve been looking to learn more about. Like his previous posts, he’s done a good job of explaining a topic so that is easy to read and understand.
If you talk to me for than five minutes about neural networks, I’ll likely mention training one to write poetry. I’m kind of obsessed. Well, the folks over at OpenAI have discovered something that would be an awesome addition to my artificially intelligent poet: sentiment. They’ve developed a model that creates a product review — character by character — with a twist. You can specify whether you want the generated review to be positive or negative by overwriting a single neuron. This post details how they discovered this “sentiment neuron” and gives some examples of generated reviews. There’s even a neat graphic that shows how the value of the neuron changes as it encounters new characters during training.