Recently at home with my mom and sister and I was explaining a bit about the work I’m going to be doing in AI for digital pathology. We got talking about how there is so much data, but a scarcity of good labels, what self-supervised learning is and how it can help overcome this. As I was describing how it works, my sister was like “oh, ya, like this!” and pulled out a coloring book my nieces had been working on. Exactly!
The theme for this year’s workshop will be “Moving beyond supervised learning in healthcare”. This will be a great forum for those who work on computational solutions to the challenges facing clinical medicine. The submission deadline is Friday Oct 26, 2018. Hope to see you there!
UPDATE: Some cool people at Georgia Tech and Google Brain have developed an interactive visualization called GAN lab which is way more exciting than this which you can check out here: https://poloclub.github.io/ganlab/
Yesterday, I wrote about Generative Adversarial Networks being all the rage at NIPS this year. I created a toy model using Tensorflow to wrap my head around how the idea works. Building on that example, I created a video to visualize the adversarial training process.
The top left panel shows samples from both the training and generated (eg counterfeit) data. Remember that the goal is to have the generator produce samples that the discriminator can not distinguish from the real (training) data. Top right shows the predicted energy function from the discriminator. The bottom row shows the loss function for the discriminator (D) and generator (G).
I don’t fully understand why the dynamics of the adversarial training process are transiently unstable, but it seems to work overall. Another interesting observation is that the loss seems to continue to fall overall, even as it goes though the transient phases of instability when the fit of the generated data is qualitatively poor.
While they hit the scene two years ago, Generative Adversarial Networks (GANs) have become the darlings of this year’s NIPS conference. The term “Generative Adversarial” appears 170 times in the conference program. So far I’ve seen talks demonstrating their utility in everything from generating realistic images, predicting and filling in missing video segments, rooms, maps, and objects of various sorts. They are even being applied to the world of high energy particle physics, pushing the state of the art of inference within the language of quantum field theory.
The basic idea is to build two models and to pit them against each other (hence the adversarial part). The generative model takes random inputs and tries to generate output data that “look like” real data. The discriminative model takes as input data from both the generative model and real data and tries to correctly distinguish between them. By updating each model in turn iteratively, we hope to reach an equilibrium where neither the discriminator nor the generator can improve. At this point the generator is doing it’s best to fool the discriminator, and the discriminator is doing it’s best not to be fooled. The result (if everything goes well) is a generative model which, given some random inputs, will output data which appears to be a plausible sample from your dataset (eg cat faces).
As with any concept that I’m trying to wrap my head around, I took a moment to create a toy example of a GAN to try to get a feel for what is going on.
Let’s start with a simple distribution from which to draw our “real” data from.
Next, we’ll create our generator and discriminator networks using tensorflow. Each will be a three layer, fully connected network with relu’s in the hidden layers. The loss function for the generative model is -1(loss function of discriminative). This is the adversarial part. The generator does better as the discriminator does worse. I’ve put the code for building this toy example here.
Next, we’ll fit each model in turn. Note in the code that we gave each optimizer a list of variables to update via gradient descent. This is because we don’t want to update the weights of the discriminator while we’re updating the weights of the generator, and visa versa.
loss at step 0: discriminative: 11.650652, generative: -9.347455
loss at step 200: discriminative: 8.815780, generative: -9.117246
loss at step 400: discriminative: 8.826855, generative: -9.462300
loss at step 600: discriminative: 8.893397, generative: -9.835464
loss at step 3600: discriminative: 6.724183, generative: -13.005814
This image comes from the cover of Preliminary Papers of the Second International Workshop on Artificial Intelligence and Statistics (1989). Someone abandoned it in the lobby of my building at school. Whatever for, I’ll never know.
I just love the idea of machine learning/AI/Statistics evoking a robot hand drawing a best fit line through some points on graph paper with a pen.
What other funny, or interesting, metaphorical visual representations of machine learning have you seen? Drop a link in the comments and I’ll get my robot arm to compile the results.