Wednesday 19 December 2012

After all, it is a "Chinese" room, not a Japanese. What do you expect?

Spaun (or Semantic Pointer Architecture : Unified Network) is a cognitive neural model of a perception-memory-motor system.

"...The model consists of 2.3 million spiking neurons whose neural properties, organization, and connectivity match that of the mammalian brain. Input consists of images of handwritten and typed numbers and symbols, and output is the motion of a 2 degree-of-freedom arm that writes the model’s responses. Tasks can be presented in any order, with no “rewiring” of the brain for each task. Instead, the model is capable of internal cognitive control (via the basal ganglia), selectively routing
information throughout the brain and recruiting different cortical components as needed for each task."

The tasks it can perform are:

1. Digit Recognition, in which a handwriting digit is given to it as an input and Spaun recognizes it with an accuracy well compared to that of humans.

2. Tracing from the memory, Spaun can not only recognize a digit and draw it as an output, it can mimic the style of the input (its font for instance).

3. Serial Working Memory, that is to repeat a sequence of numbers in the same order given to it.

4. Question Answering, it can identify a digits position within a sequence. It is a different task from the  one above in that in the previous task, it only repeats the sequence.

5. Addition by Counting, Spaun can perform mental addition via counting, which might seem an easy task, given a calculator does it pretty easily, but it is done from start to the end by the network (the recognition and probably decoding of the input and the further computation).

6. Pattern Completion,  given a training set such as :

Input: Biffle biffle rose zarple. Output: rose zarple.
Input: Biffle biffle frog zarple. Output: frog zarple.
Input: Biffle biffle dog zarple. Output: dog zarple.

It can generalize the pattern and give the following output to this:

Input: Biffle biffle quoggie zarple. 
Output: quoggie zarple.

I admit this is impressive. But, from a computational semantics point of view, I wonder, if such a model simulates a network with specified neural properties and organizations for understanding and producing language, after training it (the same way a human infant is trained), would it "understand" and produce language (appropriately)?

I came across this paper through Conscious Entities' post which in my opinion, shouldn't be missed. 
Here are some videos demonstrating each task performance by Spaun.

Wednesday 17 October 2012

Concept explosion 2045*


I can usually think of a situation in which a concept could have, for the very first time, emerged. Despite trying a lot, I couldn't do it for some abstract concepts such as "knowledge", "thought" and "consciousness", not at least without the scenario ending up implausibly funny.

----------------------------------------------------

I always wonder, have I had other sets of concepts instead of the ones I now have, would my perception of objects and events be different than what it is now? (how would my world be like if I couldn't conceive of "knowledge"?)

----------------------------------------------------

There seems to be a correlation between the number of concepts involved in human life and its complexity.  In the scientific arena, new concepts are created each day. With the limited memory capacity we have, if we were to keep and use all concepts we acquire, we couldn't function mentally. So, prioritization is essential - both in individual and collective scales - or we may end up with a pile of unnecessary, inessential concepts and if our ultimate goal is to understand/define life, with the increasing number of concepts, aren't we making it more impossible? 

Singularity makes sense.

Friday 12 October 2012

Mentally under Maintenance


After writing the thesis it seems a little too difficult to write about anything else, beside the fact that I am afflicted by the so-called "writer's block" for a while now, not that I am a writer to begin with. I guess the point is made.
-------------------------------------------------

I have recently joined a journal club of cognitive neuroscience. The first session was very appealing, the topics of discussion were just what I was looking for. Apparently there is an inclinaton towards "consciousness" and "NCC".  Also, there is a class of "molecular neuroscience" that I am going to attend, hopefully from tomorrow.

-------------------------------------------------

I have an on/off thing with "lucid dreaming". I mainly wanted to get lucid in my dreams to be able to do whatever impossible-in-"real"-life thing I want, in my dreams. But without getting lucid,  I sometimes have such fulfilling dreams that I wouldn't have dreamed of .

-------------------------------------------------

This was an attempt to break the block.

Saturday 1 September 2012

Lock or Luck?


I am starting to learn  Rock Balancing. I am going to self-learn it, and I know it might take a while until I can balance rocks like in the photo above, but it doesn't make it any less exciting for me.
Wish me luck ;-)

Monday 20 August 2012

Pot(ai)to Pot(A)to

..of course, honesty has its appeals, and is even more appealing if it's the more difficult choice, if not the most. But Lying has its own charm too, in a situation where honesty is much easier and brings pride, like when someone is asked about their achievements, or if the good deed is done by them(which is). Besides, it's unfair not to appreciate an artistic deception.

According to the Information theory: If a bit of information, say a 0, is lost on its way to a destination, and instead, another bit is randomly being generated and transmitted, be it also a 0, we cannot say that the signal has been delivered. The received data is just noise.

Suppose someone doesn't like you (merely hypothetically), and they pretend otherwise, that's like the signal is a 0 and the noise is a 1, and you might be bright, they might not be good at pretending, or vice versa, that either leads into your detecting the lie or not. Now, suppose that someone doesn't like you, but instead of pretending otherwise, they "pretend" they don't like you, in an obvious way(so that their pretension is detected, and it makes you think they like you). This is like the signal is a 0 and the noise is also a 0. Now it takes more than just smarts to spot the truth in this case. The question is, if the receiver is not smart enough to discern the pretense, is the action still a lie? or merely a complicated game in which the opponent failed to participate?

Monday 23 July 2012

the comatose worm

Is fear grounded in meaning? If one loses touch with meaning, would one still be struck by fear? What is there to be afraid of? 
I was thinking it could be generalized to other feelings such as happiness,love or hatred, but it couldn't. Apparently, fear has an unspecifiably unique quality.
According to this, I'm wondering if it is implausible not to have some level of meaning in any conscious animal who can experience fear.

Sunday 8 July 2012

Like me if you want, but don't let me think for you!

For a while, I have been busy with school, and I didn't get a chance to update the blog.
But I spent some(actually quite a lot of) time in Google Plus, and as I'm generally interested in neuroscience and cognition.. and related topics, I usually follow these kinds of posts. What I noticed about the scientific/pseudo-scientific posts ..and the interactions with them (Comments/ +1s/Shares), was how people usually by understanding only some parts of a text, or by just seeing a few familiar terms related to the topic of their interest, +1/Share it.
If someone's posts are interesting, or usually credible, it doesn't mean that we should accept whatever they say by faith. We can of course, but this lacks critical thinking. And we might obtain information this way, but not knowledge.
It's also dangerous, as it's a form of sophistry to put a desired pseudo-fact in-between a few known, accepted facts, or fabricate a seemingly coherent causal relation between them, or deviate an argument by long, correct but unrelated examples. Accepting without critical thinking and scrutinizing, instead of knowledge, leads to double ignorance.

Tuesday 15 May 2012

La Petite Mort

I was reading a rather "prescriptive" post on sexual liberalism today, which made my stream of consciousness wander around the subject. 
Not exactly related to that post..this question popped in my mind:
I've read that most mammals and some non-mammals, too, experience sexual pleasure,and some, like humans, even have orgasm. I can accept that as an evolutionary reward system for reproduction. Sex is not something like food that life depends on, and probably most of times, if not all, it takes a lot of energy to be performed.. of course for the female part it takes much more than that(the pregnancy, the labor and the rest..), if done by the purpose of procreation. So, there must be a rather huge reward to pay off these costs. 
Evolutionary speaking, that makes a lot of sense. What I'm curious about, even if considering non-mammals who perform sexual activity to procreate, as having a sort of pleasure or reward system for that, what is the reward for other types of reproduction, like the nonsexual ones, it takes a lot of work to continually reproduce..say, for a bacteria. Why even bother? or is there "a kind of" orgasm in cell division too(of course it's rather a controversial subject as it is highly implausible for a bacteria to be conscious in the first place)? But how is it paid off?

Trivia : "La Petite Mort" = "The Little Death" in french is a metaphor for "Orgasm".

Wednesday 25 April 2012

What does this big elephant do in this dark room?! (Irrelevant intentions)

Metaphorically speaking*, there's a spectrum between the blinds and the schizophrenics.

Assuming there's a firm reality out there, if blind people were the majority, would it be reasonable if they considered themselves normal & "others" liars/idiots/delusionals?(Naturally yes!)

Assuming the same thing, if schizophrenics were the majority, would it be reasonable if they considered themselves normal & "others" liars/idiots/blinds?(Naturally yes!)

The problem lies in the belief that reality is a firm, reliable experience for everyone, or else, there's something wrong with their receivers and not the reality itself.

* Since Blindness and Schizophrenia are not generally opposites.