## Bayesian Recognition

We don’t meet often, but every time we talk, she reminds me that I had failed to recognize her the first time we had met after graduating together from school. Yes, I could claim in my defence that I was seeing her for the first time in over six years. While that might be a valid excuse for most people, it doesn’t apply to me, since I normally claim to have superior long-term memory. If I’ve seen you somewhere before, I ought to recognize you. The only times I don’t I’m pretending, since I don’t want to embarrass you (and myself) by recognizing you while you don’t recognize me (see this incident for an example of this).

The reason for my failure that cold Bangalore evening in December 2006 was that my Bayesian system had failed me. Let me explain, in the process giving you an insight into my Bayesian system which I use to recognize you when I meet you.

About a month or two back, I was at a friend’s wedding, which is where I hit upon this term “Bayesian recognition” to explain this phenomenon  (which I’ve been practicing for ages). Now, this friend whose wedding I was attending was one year my junior at two different schools. As you might expect at an event where you and the host share more than one social network, there were a lot of familiar faces. Some people I knew fairly well, and could easily recognize. But the others had to go through a “Bayesian search”.

So when I saw someone who was one of three people I know – let’s say X, Y and Z. In order to determine which of these this person is, I would ask myself two questions – firstly, what were the prior odds that the person I saw could be each of X, Y or Z. Secondly, what were the odds of each of X, Y and Z being there at that event. Note that the latter is important. For example, if someone at the event looks like you and I know (for example) that you are currently in another country, despite the strong resemblance I can discount the possibility that that person is you, and go ahead with my search.

Note that this differs from “frequentist recognition”, where I only look at the person’s face and try and understand who he/she most resembles, without any thought to the odds that that person is there. Frequentist recognition can lead to a large number of false positives, and after a few rounds of embarrassment, you start giving up on recognizing, and many a possible reunion thus gets missed. Bayesian recognition, on the other hand, restricts your field of search (to the people who you give good odds of being there), prevents you from being distracted and increases your chances of making a good recognition.

So why did Bayesian recognition fail me when I met this former classmate back in 2006? The problem was her company. She had come for this Deep Purple concert with another friend of mine, who was my classmate in another school (and who I had been in touch with, and so easily recognized). I had no clue that these two were friends (it turned out they didn’t know each other that well – they had come there with a common friend). So when this girl (the one I didn’t recognize) popped up with “Hey SK! Do you remember me?” I assumed that she was someone I knew from the same school as the other girl I was meeting, and that wrongly restricted my search space. And so my mind was trying to map her to my friends from school 1, while she happened to be a friend from school 2. And my search returned a blank, and my legendary long-term memory skills were embarrassed.

I must mention here, though, that this is possibly the only time that my Bayesian recognition model has acted up, and refused to recognize someone I know. There have been 2-3 false positives, but this has been the only negative. And when you consider the sample size to be all the people I have recognized in different places, this is small indeed.

Oh, and after failing to recognize her then, I’ve kept in touch with this friend.

## Wedding Notes

I just got back from a friend’s wedding. Lots of pertinent observations.

• Today’s groom and I share three social networks. We went to two schools together and he went to a third after I had graduated from there. So I had expected to meet a lot of old friends/acquaintances. To my surprise, fifteen minutes after I had got to the wedding hall, I hadn’t “met” anyone. Finally ended up meeting just two people that I’d known.
• The queue system in receptions is much abused. It is demoralizing to get to a wedding and see that you’ve to go through such a long process before you meet the couple. As the groom (or bride for that matter), it’s even worse. You’re tired after a full day of activity and a long line of people waiting to meet you isn’t too inspiring. However, sometimes the queue turns out to be a lifesaver. It was the first time in a very long time that I’d gone alone to attend a wedding. On earlier such occasions I’d just be looking around like a fool for familiar faces. Today, though, there was no such dilemma. I headed straight to the queue!
• People who didn’t immediately join the queue had a special treat. Waiters were going around the hall offering soft drinks and starters to those that were seated. I looked to see if they served those in line also. They didn’t. I managed to sample those starters, though, when I went to meet some friends after I’d wished the couple.
• This wedding was at a fairly new wedding hall (less than ten years old for sure), and these modern halls are built in quite a streamlined manner, I must say. From the reception stage, there’s always a path that quickly leads you to the dining hall. And then from the dining hall, there is a path that leads straight outside, where paan and coconuts will be waiting for you, which you can collect on your way out. This is a much better system than in some of the older wedding halls, like the one where I got married. There, the path from the dining hall led back to the main hall, and so at times there was a traffic jam, with large numbers of people moving both to and from the dining hall.
• There’s something classy about wedding halls where chairs have been draped with white sheets and fat ribbons tied across the backs of the chairs. There’s also something classy about round tables with chairs set up in the dining hall, where you can settle down with the food you’ve picked up at the buffet. There weren’t too many of those but the set up allowed for plenty of standing room, also.
• The buffet itself was well designed. It had been separated out into several clearly marked sections. You had to collect your plate from a central location (I almost typed “central server”!! ) and go to the counter whose food you wanted. This prevented long lines and bottlenecks. It was a pleasant food experience.
• There were some five different kinds of sweets. Given that it’s hard to estimate demand for each, I wonder how they would’ve tackled the wastage.
• When you meet old friends, after a while the conversation invariably degenerates to “so, who did you meet of late? what’s he/she doing?” and you end up going through your class roll call and try figure out who’s doing what.
• I’ve said this before but I’m not at all a fan of live music at weddings. Keep it too soft (never happens) and the artistes get pissed off. Keep it too loud (always the case) and you need to shout to be heard. Some weddings take it a step forward – they pipe the music from the main hall where it’s being played live into the dining hall, killing conversation there too. There are piracy issues there but I still like what we did at our wedding, when we played a carefully curated set of trance numbers. I don’t know how well it was received, though, and how loud it was (we couldn’t hear anything on stage).
• Some “features” that used to be luxuries at wedding receptions ten-fifteen years ago are necessities now. Chaat, soup, paan, ice cream, that table in the centre with huge carved vegetables and salads ..