Summary: Many machine learning systems are optimized using metrics that don't perfectly match the stated goals of the system. These so-called "proxy metrics" are incredibly useful, but must be used with caution.
The use of so-called proxy metrics to solve real-world machine learning problems happens with perhaps surprising regularity.I have written before about the repercussions of optimizing a metric that doesn't perfectly align with the stated goal of the system. Here, I touch upon why the use of such metrics is actually quite common. The choice to solve an alternative metric, in which the optimization target is different from the actual metric of interest, is often a conscious one. Such metrics have proven incredibly useful for the machine learning community — when used wisely, proxy metrics can be used to accomplish tasks that are otherwise extremely difficult. Here, I discuss a number of common scenarios in which I see machine learning practitioners using these proxy metrics and how this approach can sometimes result in surprising behaviors and problems.
I have written before about the repercussions of optimizing a metric that doesn't perfectly align with the stated goal of the system. Here, I touch upon why the use of such metrics is actually quite common.
It is especially easy at the beginning of a new year to fall into the trap of the New Year's Resolution. New goals and challenges and routines are established under the banner of self-improvement. Gyms and fitness centers become packed. Productivity books fly off the shelves. In the words of The New Yorker's Alexandria Schwarts, we're improving ourselves to death and in our crusade to make time for all this self-improvement, hobbies are too often forgotten.
What I've discovered over time is that many of my skills and passions have developed only through little side-projects that never see the light of day.
For me, hobbies walk an enjoyable line between work and play: I often aim to learn something or try something new. Hobbies afford me the opportunity to challenge myself and embrace failure without worry of repercussion. A couple years ago, during a self-imposed redesign of this blog, I came across Robert Bringhurst's fantastic book, The Elements of Typographic Style. Captured by his prose on the art of typography and font design, I started exploring and my website became an outlet for experiments in typography. My exploration grew to include other types of graphic design, and I've been experimenting with design software and creating vector art ever since.
Mastery has never been the goal: learning something new and having an outlet for my creativity are their own rewards. But despite the independent nature of my exploration, making high-quality graphs and figures became easier and the quality of my technical presentations at work has clearly improved.
Summary: Big, publically available datasets are great. Yet many practitioners who seek to use models pretrained on outside data need to ask themselves how informative the data is likely to be for their purposes. "Dataset bias" and "task specificity" are important factors to keep in mind.
As I read deep learning papers these days, I am occasionally struck by the staggering amount of data some researchers are using for their experiments. While I typically work to develop representations that allow for good performance with less data, some scientists are racing full steam ahead in the opposite direction.
It was only a few years ago that we thought the ImageNet 2012 dataset, with 1.2 million labeled images, was quite large. Only six years later, researchers from Facebook AI Research (FAIR) have dwarfed ImageNet 2012 with a 3-billion-image dataset comprised of hashtag-labeled images from Instagram. Google's YouTube-8M dataset, geared towards large-scale video understanding, consists of audio/visual features extracted from 350,000 hours of video. Simulation tools have also been growing to incredible sizes; InteriorNet is a simulation environment consisting of 22 million 3D interior environments, hand-designed by over a thousand interior designers. And let's not forget about OpenAI either, whose multiplayer-game-playing AI is trained using a massive cluster of computers so that it can play 180 years of games against itself every day.
AlphaZero is incredible. If you have yet to read DeepMind's blog post about their recent paper in Science detailing the ins and outs of their legendary game-playing AI, I recommend you do so. In it, DeepMind's scientists describe an intelligent system capable of playing the games of Go, Chess, and Shogi at superhuman levels. Even legendary chess Grandmaster Garry Kasparov says the moves selected by the system demonstrate a "superior understanding" of the games. Even more remarkable is that AlphaZero, a successor to the well-known AlphaGo and AlphaGo Zero, is trained entirely via self-play — it was able to learn good strategies without any meaningful human input.
So do these results imply that Artificial General Intelligence is soon-to-be a solved problem? Hardly. There is a massive difference between an artificially intelligent agent capable of playing chess and a robot that can solve practical real-world tasks, like exploring a building its never seen before to find someone's office. AlphaZero's intelligence derives from its ability to make predictions about how a game is likely to unfold: it learns to predict which moves are better than others and uses this information to think a few moves ahead. As it learns to make increasingly accurate predictions, AlphaZero gets better at rejecting "bad moves" and is able to simulate deeper into the future. But the real world is almost immeasurably complex, and, to act in the real world, a system like AlphaZero must decide between a nearly infinite set of possible actions at every instant in time. Overcoming this limitation is not merely a matter of throwing more computational power at the problem:
Using AlphaZero to solve real problems will require a change in the way computers represent and think about the world.
Yet despite the complexity inherent in the real world, humans are still capable of making predictions about how the world behaves and using this information to make decisions. To understand how, we consider how humans learn to play games.
The modern revolution in machine learning and robotics have been largely enabled by access to massive repositories of labeled image data. AI has become synonymous with big data, chiefly because machine learning approaches to tasks like object detection or automated text translation require massive amounts of labeled training data. Yet obtaining real-world data can be expensive, time-consuming, and inconvenient. In response, many researchers have turned to simulation tools — which can generate nearly limitless training data. These tools have become fundamental in the development of algorithms, particularly in the fields of Robotics and Deep Reinforcement Learning.
This is the first post in a three-part series on the role of simulated image data in the era of Deep Learning. In this post, I discuss the significance of simulation tools in the field of robotics and the promise and limitations of photorealistic simulators.
It is a sort of running joke to blame cosmic rays for unrepeatable bugs in computer code. In reality, it's more likely that your RAM is bad or that your CPU has an implementation bug. Yet there remains something exciting — if terrifying — about the idea of light coming down from the heavens and flipping a single bit, rendering your compiled program unexpectedly useless. As such, the legend persists.
Readers who know me well may recall that my Master's thesis was in the field of high-peak-power lasers. Our lab studied, among other things, a process by which room-sized lasers could be used to coherently excite electrons and thereby convert light from infrared frequencies into X-raysThe long-term goal was the creation of an X-ray laser, which could be used for medical imaging; it's probably over a decade away from practical use. . Since the conversion process was pretty weak, we needed extremely sensitive detectors that were capable of responding to single photons.
The long-term goal was the creation of an X-ray laser, which could be used for medical imaging; it's probably over a decade away from practical use.
The high sensitivity of the photodetector was a mixed blessing: we needed it to detect the weak signal produced by our experiment, but it amplified other sources of noise as well. During data collection, the detector would occasionally have massive spikes in the output readings, which would saturate parts of the image at the output. If we left the detector on for too long, the resulting image would be filled with scattered noise that could overwhelm our signal.I did a bit of digging and found an article entitled Background Events in Microchannel Plates that suggests that cosmic rays make up only about 4% of background noise events for the detectors we used. A small factor for sure, but not insignificant either. Thermal fluctuations, nuclear radiation, and cosmic rays were all contributors to the difficulties in the experiment. There was nothing we could do to lower this noise floor: the universe was our enemy.
I did a bit of digging and found an article entitled Background Events in Microchannel Plates that suggests that cosmic rays make up only about 4% of background noise events for the detectors we used. A small factor for sure, but not insignificant either.
As the use of machine learning systems grows beyond the academic sphere, one of the more worrying features I have witnessed is a lack of understanding of how machine learning systems should be trained and applied. The lessons the AI community has learned over the last few decades of research are hard-earned, and it should go without saying that those who do not understand the inner workings of a machine learning toolThis advice is not limited to AI. Using any stochastic system without an understanding of when or how it is likely to fail comes with inherent risk. risk having that system fail in often surprising ways.
This advice is not limited to AI. Using any stochastic system without an understanding of when or how it is likely to fail comes with inherent risk.
However, the potential advantages of AI are many, and using machine learning to accelerate your business, whether empowering employees or improving your product, may outweigh potential pitfalls. If you are looking to use machine learning tools, here are a few guidelines you should keep in mind:
- Establish clear metrics for success.
- Start with the simplest approach.
- Ask yourself if machine learning is even necessary.
- Use both a test and a validation dataset.
- Understand and mitigate data overfitting.
- Be wary of bias in your data.