Welcome to
Caches to Caches

This blog is devoted to the broad interests of Gregory J Stein, which includes topics such as Numerical Modeling, Web Design, Robotics, and a number of my individual hobby projects. If there's any article you would like to see, or something you've been wondering about, be sure to let me know on Twitter.

I can't tell you the number of articles I've read devoted to "debunking myths". They try to communicate the author's opinion by listing a set of negative examples, often with section headings labeled Myth #1, Myth #2, etc. At best, it's an easy way of building up a straw-man argument, yet at worst, such an article confuses the reader, filling their screen with potentially contentious or confusing statements. Try as I might, I rarely find these Myth List articles compelling. One particularly problematic article I recently came across boasted a headline of the form "10 Myths about […]" whose in-article headings were simply all the myths. At the start of every new section, I needed to remind myself that the author's belief was opposite to what was written on the page. As you might imagine, the article was far from compelling.

Worse still are articles in which the author's goal is to persuade rather than inform, and whether or not myths are actually myths is a contentious point.

The mental hoops I sometimes have to jump through to figure out what the author is trying to communicate rarely outweigh the benefits they might have gotten by introducing an opposing viewpoint. In succinctly summarizing only a point of view that is not being arguing for, the author introduces a cognitive dissonance in the reader that need not exist. Many such articles could benefit from a more clearly presented statement of the author's viewpoint. Even having both views side-by-side would be a massive improvement, and could be made even clearer by adding visual markers to indicate which statement agrees with the author's. Particularly in the modern era in which online attention span is limited and skimming is the norm, it is to the author's benefit to make their article as skimmable as possible. Myth lists are in direct conflict with this goal, since the author's perspective is often only fleshed out in the body of the text.

Summary: Recent ire from the media has focused on the high-power consumption of artificial neural nets (ANNs), yet popular discussion frequently conflates training and testing. Here, I aim to clarify the ways in which conversations involving the relative efficiency of ANNs and the human brain often miss the mark.

I recently saw an article in the MIT Tech Review about the "Carbon Footprint" of training deep neural networks that ended with a peculiar line from one of the researchers quoted in the article:

'Human brains can do amazing things with little power consumption,' he says. 'The bigger question is how can we build such machines.'

Now I want to avoid putting this particular researcher on the spot since his meta-point is a good one: there are absolutely things that the human brain is readily capable of for which the field of Artificial Intelligence has only just begun to scratch the surface. There are certain classes of problems, e.g. navigation under uncertainty, that require massive computational resources to solve in general, yet humans are capable of solving very well with little effort. Our ability to solve complex problems from limited examples, also known as combinatorial generalization, is unmatched in general by machine intelligence. Relatedly, humans have incredibly high sample efficiency, and require only a few training instances to generalize performance on tasks like video game playing and skill learning.

Yet commenting on the relative inefficiency of the neural net training, particularly for supervised learning problems, misses the point slightly. Deep learning has been shown to match and even (arguably) surpass human performance on many supervised tasks, including object detection and semantic segmentation. For such problems, the conversation about relative energy expenditure — as compared to the human brain — becomes more nuanced.

Summary: Machine learning must always balance flexibility and prior assumptions about the data. In neural networks, the network architecture codifies these prior assumptions, yet the precise relationship between them is opaque. Deep learning solutions are therefore difficult to build without a lot of trial and error, and neural nets are far from an out-of-the-box solution for most applications.

Since I entered the machine learning community, I have frequently found myself engaging in conversation with researchers or startup-types from other communities about how they can get the most out of their data and, more often than not, we end up taking about neural networks. I get it: the allure is strong. The ability of a neural network to learn complex patterns from massive amounts of data has enabled computers to challenge (and even outperform) humans on general tasks like object detection and games like Go. But reading about the successes of these newer machine learning techniques rarely makes clear one important point:

Nothing is ever free.

When training a neural network — or any machine learning system — a tradeoff is always made between flexibility in the sorts of things the system can learn and the amount of data necessary to train these systems. Yet in practice, the precise nature of this tradeoff is opaque. That a neural network is capable of learning complex concepts — like what an object looks like from a bunch of images — means that training it effectively requires a large amount of data to convincingly rule-out other interpretations of the data and reject the impact of noise. On the face of it, this statement is perhaps obvious: of course it requires more work/data/effort to extract meaning out of more complex problems. Yet, perhaps counterintuitive to the thinking of many machine learning outsiders, the way in which these systems are designed and the relationship between the many complex hyperparameters that define them has a profound impact on how well the system performs.

Noise takes many forms. In the case of object detection, noise might include the color of the object: I should be able to identify that a car is a car regardless of its color.

In my role as a Communication Advisor for the MIT Communication Lab, I see a lot of practice talks. Students, both graduate and undergraduate, sign up for a 30 minute or 1 hour long session during which they will present some material they're working on and ask for guidance on both content and presentation: "How clear is what I was trying to accomplish?" or "Are my results figures clear?"

Rarely do students ask "Did I use too much jargon?" It likely doesn't occur to them that, despite their relative inexperience, they might know more about the subject at hand than those to which they are presenting.

One of the key components to good technical communication is the right amount of context. Provide too much background material and your audience will lose interest; too little, and the audience may not be able to follow the remainder of the talk. The first half of a talk should clearly communicate Why the audience should care about your work and How your work compares to other work in the field. Addressing these questions often requires an understanding of popular trends within a discipline or how common certain tools or tricks are.

It should come as no surprise that newer researchers, typically undergraduates or first/second-year graduate students, may find it difficult to decide what information to include when preparing a talk. More frequently than not, I find that most technical talks — particularly those from newcomers to the field — spend too much time discussing the nitty-gritty details of an experiment while leaving out important details about the motivation of their research. Talks from neophyte researchers often vacillate between including an overwhelming amount of detail to covering unnecessary minutiae or unknowingly including too much jargon when explaining difficult concepts, likely in an effort to seem experienced. It is not uncommon for such presentations — in the space of two slides — to transition from an in-depth description of background material that the audience might consider "common knowledge" to a hastily-done description of domain-specific information essential for understanding the remainder of the talk. To make matters more complicated, the composition of the audience must be taken into consideration when deciding what material needs to be addressed during the talk: what one group might decide is "common knowledge" may be completely foreign to another.

Preparing a talk requires understanding one's audience and, without external support, only experience yields such knowledge. Technical communication is understandably hard for newcomers. Not only do they have trouble fully appreciating what they know and don't know, it's also extremely difficult for them to understand what others around them know. Good mentorship is critical for shaping a younger student's perspective in this regard. Such students should seek out feedback from more established members of the community and experienced communicators should make themselves available to provide support.

As always, I welcome your thoughts (and personal anecdotes) in the comments below or on Hacker News.

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. 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.