Transcendental - a number that can’t be represented algebraically. (using +-*/, or raising to a power, even a fractional one) 7 is an important number. It has an incredible history of cultural significance. I wonder if with working memory; less is more. Does having a limited capacity to store information require that abstractions be made such that the required complexity is kept within manageable bounds. The wiki page on the importance of 7 recently came up on hacker news. I have over the last year developed what I think is an idea that could possibly lead to a general intelligence. It is my belief that it does not require a large amount of computation to emulate the aspects of intelligence that we attribute to intelligent people. Clearly to be able to derive the function that maps from the space of a 4k video to categories which include a tortoise or turtle is going to be an intensive one to compute. What you are trying to do is something that involves a large amount of informat...

I have many google homes in my flat. I use them to turn on the lights, set timers, do unit conversions and play ocean sounds. I wouldn’t consider their speech recognition to be good. My girlfriend with her feminine voice has an even harder time with them, often resorting to putting on a comedic deeper voice to get google to recognise her commands. I’ve looked into how speech recognition is done and when building my computer back in January one of the goals I had for it was to train my own language model. I’ve written about ideas I have for getting the computer to recognise language before. My understanding of the most up-to-date techniques for language recognition is to use a CTC network to train between the audio and words. The training data that is used is labelled speech. That would consist of a mp3 file of someone saying a sentence and then a text file or record of that sentence. The audio file will then be decomposed into a frequency analysis creating an image like the following w...

I have before briefly mentioned a definition for intelligence that is useful to consider when investigating AI. I’d like to go deeper into what my understanding of intelligence is. I have a deep interest in understanding the fundamentals of intelligence, what is it really that allows humans to outperform machines that are by most measures far superior in their computational power. I discuss a lot with friends and colleges the facets of what they believe intelligence to be and what different elements mean. This search has not just led to a Masters in artificial intelligence but to look deeper to read numerous books on epistemology, a topic I believe was missing in my degree. Epistemology is the study of knowledge. By most measures of intelligence and especially in its colloquial use intelligence has something to do with knowledge. Epistemology is the school of philosophy dedicated to making arguments about what it means to know something. It goes a lot deeper into the topic than the qu...

Say you had been able to make a general AI. Given the level of intelligence, it has you would have thought booking you a holiday would be a simple task. And it would be if it weren’t for robots.txt and the terms and conditions websites have against non-human agents using their services. Ryanair for example forbids booking using any automated system. That means that although your AI is quite capable of booking your holiday it would actually break the terms and conditions of your holiday for it to do so. Will this be an issue? It does cause an issue, for the time being, lots of companies have to employ low paid workers to crawl through sites in a way that a simple spider program could do with far more efficiency just because the websites that would be scraped forbid that scrapers are used. It doesn’t matter if the websites know that the agent opening their website is a human or not, there will always be ways to fake being human online. The issue arises more from the legal challenges that...

  Invariance, as opposed to inflammable, means, does not vary. The phrase “invariant in time” simply means “not changing over time”. Einsteins theory of relativity is all based on trying to create a consistent view of the world where certain things shouldn’t change depending on who is measuring them and how they are being measured. Invariance is important in artificial intelligence too. It’s incredibly important because if you can assume something won’t change, you don’t have to perform a calculation working out how it has changed. Take the simple example of newtons laws of motion, summarised in the formula: F=ma The power of this formula lies it its invariance. It doesn’t vary with the day of the week or time of day. It doesn’t vary with shape, with the type of object, with who is in government. It doesn’t vary with who is looking at it or where they are. Physics is assumed to be invariant with things such as the political persuasion of the observer but why can we make that assump...

What is intelligence? In artificial intelligence, there is a generally agreed-upon definition that intelligence is “The ability of an agent to correctly choose actions manipulating the world so as to achieve its terminal goal” . This definition is much easier to formalise and work towards than the more vague and anthropomorphic colloquial definition. That does mean that there are differences which might make the use of the term with this definition counterintuitive thinking in terms of the other. A common argument within my family is the question of if good recall constitutes intelligence (Not on its own according to this definition). An objection to this definition is that Donald Trump is considered intelligent, given his ability to take actions to achieve his goals (*Update post election, perhaps he is as lacking as he seems) . Other objections to this definition relate to how easier goals might make agents relatively more intelligent. Having an easier goal might make it seem that a...

One of the things I want to achieve through the blog is the ability to compose a small project in an evening. Rather than just have ideas that never get implemented into even the most basic of MVP, the blog would encourage that I move to build my ideas quickly. Moving back to javascript has helped with that as the setup required to be able to get something visual working on an HTML5 canvas is much smaller than the equivalent elsewhere. Javascript was the language I started learning when I first learnt to code. It was the easiest to run because every computer already had a browser and notepad.exe. One of the things I like to do is create something akin to computational art and that is what I would argue I have done in this week's post. Artificial intelligence has been a long time interest of mine and one element of that is the interaction of agents. In this post, I have created a system of creatures which live in a world inspired by agar.io . If you are not familiar with the game i...

Computational omnipotence ; unlimited computing speed and memory such that if a result is computable, it can be computed. Computable ; There exists an algorithm which can produce the result in a finite number of steps Uncertainty is a topic I think everyone understands to a certain degree. There is a field of mathematics dedicated to demystifying its nebulous nature. This is, of course, the field of probability theory. There is, however, a limit to probability theory which comes from one of the assumptions that underpins it. Computational omnipotence is assumed when dealing with the calculations. That is to say that given the information you have, you can calculate all of the resulting probabilities that are possible to calculate with the starting information you have. Your uncertainty is limited to uncertainty about the environment. For example, when a die is rolled you are uncertain of which face will land up. If n dice are thrown you are only uncertain about which faces will be on t...

Conversational agents or chatbots have been an interest of mine for a very long time. I wrote my first chatbot LIRA with a friend back around 2008. It used the Alicebot dataset to try and match what the user had said with one of the tens of thousands of pre-programmed replies. In fact, all the program did was take the user input and remove a word from the end until the SQL query: This led to some funny responses albeit not very useful ones. My latest attempt to understand natural language processing and produce a chatbot has been slow progress but there are two main ideas at the core of where I want to take the project. To parse a sentence means to break the sentence into its components and generate the structure from a grammar (Find what rules make that sentence). A grammar is a series of rules that define the structure of a sentence. A parse tree is a representation of the sentence after the structure from the grammar has been added. Dealing with ambiguous grammars T...