Thoughts on… truth

Didier Dubois and Henri Prade wrote the following quote in a 1988 book entitled Non-standard  Logics for Automated Reasoning:

A degree of truth is not a degree of uncertainty about truth.

This is a very important quote, and gets right to the matter I’d like to highlight. It distinguishes those problems with truth which are answered by two distinct, but related theories.

To answer the question of “a degree of uncertainty about truth”, something known as “Probabilistic Logic” was created. This merged together classical forms of logic, with its propositions and predicates, with Bayesian (or Bayesian-style) probability theory. It puts probability theory in a subjective perspective, and assigns probabilities to rules and statements, without the need for a frequency-based possible-worlds probability calculation.

As Didier and Henri rightly point out however, this really should not be confused with “a degree of truth”. For a degree of truth, fuzzy theory (i.e. fuzzy set theory and fuzzy logic) holds the solution. Fuzzy theory allows an object or statement to have a degree of membership of a set or a particular scenario.

For example “John is tall”. Tall is a vague concept, and “John” has a degree of truth of belonging to the vague “tall” concept. This is how fuzzy set theory, and matches our human way of thinking about tallness.

From a probabilistic logic perspective we would need to ask “what is the probability that John is Tall?”, which is quite a different question.

Of course, this is an area which has, for some reason, been a thorn in the fuzzy theorists side. There are many more probability theorists in this world at the moment, than there are fuzzy theorists. Once you start working with probability theory, it is easy to apply it to everything, even if it doesn’t quite fit. There are also some strong believers of probability theory, often labelled “Bayesians”, which attempt to assert that fuzzy set theory and fuzzy logic is somehow weak because the models can be “made-up” by experts instead of generated through statistics. Many fuzzy theorists have argued back, saying that its flexible model is actually a strength and not a weakness.

My own (current) research draws heavily from fuzzy set theory, but it (i.e. my current research) also has an element of probability theory as it implements data mining algorithms such as association rule mining and sequence pattern mining, which have a statistical element. I’m keen to investigate some more areas of the overlap between fuzzy and probability theories, as I consider them both to have a place (as do most other fuzzy theorists in fact). Of particular interest is the relationship of Fuzzy Formal Concept Lattices and Credal Networks. (Credal Networks are (and I simplify here) Bayesian Networks with added imprecision).

Let me know your thoughts on the above, and whether you have any hints or tips on the above. Feel free to email me or post a message in the comments box on this blog post.

CI Unconference UK 2014 – Organisers Report

The following post was originally posted at:

http://ciunconference.org/uk/2014/report.php

 

Computational Intelligence Unconference UK 2014 on Saturday 26th July 2014 at BT Centre, Newgate Street London

CI Unconference UK 2014: http://ciunconference.org/uk/2014/

Organisers Report

Report Written on Monday 28th July 2014 by Daniel Lewis

 In short, the day went incredibly well, and I would consider it to be a success.

The talks were of very high quality, and when they were given to our attendees the talks became high quality discussions.  This was largely due to a good amount of questions and comments from the group, and also the time-cushions between talks that I had scheduled. Thank you to the speakers!  Talks were split over two rooms, with longer talks and large-group discussions happening in the 170-seater “Auditorium”, and shorter talks and smaller-group discussions happening in the 40-seater “Media Suite”. We also had Damien and Viktoriya give demonstrations during lunchtime of the Micro Python kit. Also, Andrew Vladimirov gave demonstrations through the whole afternoon of his brain monitoring and brain stimulation devices. Both demonstrations received much attention, and a good amount of dialogue.

Some videos, and a good amount of still photos, were taken of the day, and will be available to find via this years event website (along with slides from the talks). The event was supported by the volunteers, and a big thank you from all attendees go to: Beki, Marcelo, Dennis, Steve, Cathy and Abi. The event was also live-documented by attendees via twitter with the hash-tag #CIUUK14. I suspect that blog posts and other forms of report will appear online in due course.

The venue was sponsored by the BT Innovate and Design Team (based at Adastral Park, Martlesham Heath (near Ipswich), Suffolk), and was hosted at the BT Centre at 81 Newgate Street, London. On behalf of all the attendees I thank BT for helping us get the unconference running, from those that sponsored the event, to the production team, the AV team and the reception & security teams. A special mention to Rebecca, Monika, Nick and Nick, who helped us a huge amount on the day itself.

The food and drink was sponsored by:

  • Gold Sponsors – Storybricks,
  • Silver Sponsors – RecSys, EF and Oxford University Press,
  • Bronze Sponsors – futuretext and The Human Memome Project

and was provided by the BT Centre Catering team. A big thank you to all of our sponsors on behalf of all of the attendees.

However, there are a few lessons learned. 

Attendance rate. We had approximately 180 people attend, with most attending the entire day (10am – 6pm). Although this is a very healthy number and turned-out to be a good number, it is approximately a 45% no-show rate from our original 325 bookings. Such a high no-show rate is usual when free tickets are involved. However, we will be looking to investigate how we might get a lower no-show rate next year. This might involve either a two-tier ticketing system (for waged a very-low ticket price and unwaged/students at no ticket price), or a donations-based ticket approach where an attendee decides how much they pay based on how much they can afford and how much they think it will be worth. Of course revenue from these methods would go straight into the event itself, and the event would retain its completely non-profit status.

Scheduling. One thing that seemed to be quite essential was that many attendees seemed to expect a printed copy of the schedule. Although this is quite understandable, it is a little worrying as the nature of unconference is quite free-flowing, and we had moved some of the talks to up to 15 minutes earlier during the day, and actually scheduled in a tea & coffee break which did not exist prior to the day. We will ensure that in the future we have printed copies of the schedule, however, we’ll have to ensure somehow that attendees are aware of changes as they happen.

Temperature. We are aware that the temperature of the Media Suite got quite high, I personally spoke to the events production manager at the BT Centre about this, and the cooling system was at full power. Unfortunately it got too warm simply because the room being at (or possibly above) maximum capacity at times, also with people using laptops and mobile devices, and the temperature from outside (it was a very hot summers day outside!).

Video. Many people, both attendees and some who could not attend, wished to have videos of all talks (and some wanted video of the demonstrations). Unfortunately we had not arranged this fully, this was simply a matter of human error. That said, we managed to arrange for two people to come in last minute to video the talks. One turned up (Jamie (thank you!)), and one did not. We could have organised for the BT Centre to bring somebody in to record the auditorium talks with their equipment, however, this would have cost quite a large amount of money for which we did not have the sponsorship.

Lunch. We had ordered sandwiches for 200 people, and we had approximately 160 attendees wanting lunch. The sandwiches all disappeared within 15 minutes. We also had several bowls of fruit, which largely disappeared quite quickly. Nobody mentioned to me that there was not enough lunch, although I suspect that it was quite simple and some attendees may have still been quite hungry. The cost of the lunch, the tea and coffee in the morning and afternoon, and the labour equated to 1212 GBP (which is inclusive of VAT). This was a “haggled-down” price in order to achieve 100% funding. If we are to have a better lunch, we will need to receive more sponsorship, or investigate other forms of revenue. We are, of course, thankful for the food and drink we did receive, and a big thanks go (again) to the sponsors listed earlier in this report.

We have started to think about next year. 

We would like to organise another CI Unconference in Summer 2015, in London (UK). However, I’d like to put together an organisation team, as collectively we can do more than just a single (or couple of) individual(s) organising everything. If you, dear reader, would like to help out, then please let me know. We will also need sponsors, speakers, and on-the-day volunteers. We also need to think about venues. If you can help with any of this, please do email me with CI Unconference UK 2015 in the subject. I will be part of such an organisation team, however, it will become increasingly more important as I am due to finish my PhD in late 2015!

I also have some initial ideas of running CI Unconferences in the USA and elsewhere in Europe. A few of the attendees of the UK 2014 unconference have given me a few suggestions, but I’d like to get some interest from those in USA and Europe, to see if it would be worth doing. If you are interested then please do let me know by sending me an email with CI Unconference USA/Europe in the subject.

Finally, I am keen to find out if there are success stories from the CI Unconference UK 2014. The best way to do this is for attendees (particularly those who hadn’t met before the event) to stay in contact with each other. I would be keen to find out if new projects have been started because of the event. Or, if somebody got a job or a new contract because of the event. Or, perhaps you learnt something which will change the way that you work. Or anything else, personal, academic or professional! Send me an email, or maybe tweet it with the hash-tag #CIUUK14.

To conclude, this years event was incredibly successful, and I look forward to working with you all on making the next one bigger and better.

Daniel Lewis