Machine learning is a field that threatens to both augment and undermine exactly what it means to be human, and it’s becoming increasingly important that you—yes, you—actually understand it.
I don’t think you should need to have a technical background to know what machine learning is or how it’s done. Too much of the discussion about this field is either too technical or too uninformed, and, through this blog, I hope to level the playing field.
This is for smart, ambitious people who want to know more about machine learning but who don’t care about the esoteric statistical and computational details underlying the field. You don’t need to know any math, statistics, or computer science to read and understand it.
Variational autoencoders were introduced to efficiently to solve the inference problem in deep generative models. A generative model generates data by sampling as follows: z ~ p(z), x ~ p(x|z). p in this case can be modeled using deep neural networks. But using deep neural networks makes it difficult to infer z, given an x. This paper introduces a novel method based on calculus of variations to approximately infer z given x. The authors start with an intuitive objective to optimize, reduce it to the problem of optimization of a variational lower bound and finally illustrate an example using deep neural networks to model the probability distributions. In contrast to GANs (which can easily diverge even with small variations), variational autoencoders are easier to train. Similar to GANs, trained variational autoencoders have be used to generate new images and interpolate between images.
Deep Learning Research Review Week 2: Reinforcement Learning
This is the 2nd installment of a new series called Deep Learning Research Review. Every couple weeks or so, I’ll be summarizing and explaining research papers in specific subfields of deep learning. This week focuses on Reinforcement Learning.