Related
I want to improve ibm’s Watson assistant results.
So, I want to know the algorithm to determine a dialog in Watson assistant’s conversations.
Is it a svm algorithm?
A paper is welcome.
There are a number of ML/NLP technologies under the covers of Watson Assistant. So it's not just a single algorithm. Knowing them is not going to help you improve your results.
I want to improve ibm’s Watson assistant results.
There are a number of ways.
Representative questions.
Focus on getting true representative questions from the end users. Not only in the language that they use, but if possible from the same medium you plan to use WA on (eg. Mobile device, Web, Audio).
This is the first factor that reduces accuracy. Manufacturing an intent can mean you build an intent that a customer may never ask (even if you think they do). Second you will use language/terms with similar patterns. This makes it harder for WA to train.
Total training questions
It's possible to train an intent with one question, but for best results 10-20 example questions. Where intents are close together then more examples are needed.
Testing
The current process is to create what is called a K-Fold Cross validation (sample script). If your questions are representative then the results should give you an accurate indicator of how well it is performing.
However, it is possible to overfit the training. So you should use a blind set. This is a 10-20% of all questions (Random sample). They should never be used to train WA. Then run them against the system. Both your Blind + K-Fold should fall within 5% of each other.
You can look at the results of the K-Fold to fix issues, but blind set you should not. Blinds can go stale as well. So try to create a new blind set after 2-3 training cycles.
End user testing.
No matter how well your system is trained, I can guarantee you that new things will pop up when put in front of end users. So you should plan to have users test before you put it into production.
When getting users to test, ensure they understand the general areas it has been trained on. You can do this with user stories, but try not to prime the user into asking a narrow scoped question.
Example:
"Your phone is not working and you need to get it fixed" - Good. They will ask questions you will never have seen before.
"The wifi on your phone is not working. Ask how you would fix it". - Bad. Very narrow scope and people will mention "wifi" even if they don't know what it means.
I'm not sure if this is the right place to ask this, but here goes.
I have been a programmer for about 12 years now with experience in php, java, c#, vb.net and asp. I have always been rather intrigued about Artificial Intelligence. I think it is really the ultimate challenge for any developer.
I have written many simple scripts to play games but nothing compared to what I want to do next. I want to write an AI program that will play a MMORTSG (Massively Multiplayer Online Real Time Strategy Game. I have been searching through many AI techniques but none seem to tackle the problems that I know I will face:
Problems I can foresee:
The game has no "win situation", instead, the best strategy is the one that has the greatest growth in comparison to that of other players. Growth is determined by 3 factors, economy, military and research.
Parts of the game state are unpredictable. Other players can attack me at random.
The game is time based and actions take time. ie. Building a new building make take several hours. While that building is being built, no other buildings can be built.
All the AI systems I have researched, require some sort of "Winning Function" to test if the AI has found an end. Where in my situation it would more likely be something like "I have X, Y, Z options, the best one is X".
ps. Sample code would be awesome. Even Psuedo would be great.
I've seen a few applications of Artificial Intelligence in the Gaming area, but most of this was for FPS, MMORPGs and RTS games. The genre type that you appear to be relating to sounds similar to 'Clash of Clans', where research, military and economy as well as random attacks occur over a random period of time, and runs over an endless period of time.
It seems that a model would be used at key points in the game (building is finished, or research is available, or castle is full) to make strategic decisions for progression. Perhaps a Genetic Algorithm could be applied at key moments determine a suitable sequence of future steps. A modular neural network could be defined to decide the logical Growth factor to take, but training such a network may be difficult as the game rules can change over time (either from previously unknown resources, research options, military and even game updates). Scripts are quite common as well in the MMORPG genre, but defining the manual rules could also be difficult without knowing all of the available options. The fact is that there are so many ways that your challenge can be addressed that it would be difficult to give a clear-cut answer to your problem, let alone the code or psudocode.
Looking briefly over the problem, it appears that the contributing factors to the problem would be current economic state, current military state, current research state, time lost if saving for next upgrade, time required to build next upgrade, cost of upgrade as well as other unknown factors.
Given that the problem has no clear winning objectives, I guess it is a matter of maintaining a healthy balance between the three growth factors. But how does one define the balance? Is research more important? Should you always have money, or just save enough for the next planned upgrade? Should military be as large as possible?
The challenge that you are placing before yourself is quite adventurous, but I would recommend taking on smaller challenges if you are not yet familiar with the models that AI have to provide. There are quite a number of Gaming Applications for AI resources available to inspire your model (including ziggystar's examples noted above).
I need help to chose a project to work on for my master graduation, The project must involve Ai / Machine learning or Business intelegence.. but if there is any other suggestion out of these topics it is Ok, please help me.
One of the most rapid growing areas in AI today is Computer Vision. There are many practical needs where the results of your Master Thesis can be helpful. You can try research something like Emotion Detection, Eye-Tracking, etc.
An appropriate work for a MS in CS in any good University can highlight the current status of research on this field, compare different approaches and algorithms. As a practical part, it makes also a lot of fun when your program recognizes your mood properly :)
Netflix
If you want to work more on non trivial datasets (not google size, but not trivial either and with real application), with an objective measure of success, why not working on the netflix challenge (the first one) ? You can get all the data for free, you have many papers on it, as well as pretty good way to compare your results vs other peoples (since everyone used exactly the same dataset, and it was not so easy to "cheat", contrary to what happens quite often in the academic literature). While not trivial in size, you can work on it with only one computer (assuming it is recent enough), and depending on the type of algorithms you are using, you can implement them in a language which is not C/C++, at least for prototyping (for example, I could get decent results doing things entirely in python).
Bonus point, it passes the "family" test: easy to tell your parents what you are working on, which is always a pain in my experience :)
Music-related tasks
A bit more original: something that is both cool, not trivial but not too complicated in data handling is anything around music, like music genre recognition (classical / electronic / jazz / etc...). You would need to know about signal processing as well, though - I would not advise it if you cannot get easy access to professors who know about the topic.
I can use the same answer I used on a previous, similar question:
Russ Greiner has a great list of project topics for his machine learning course, so that's a great place to start.
Both GAs and ANNs are learners/classifiers. So I ask you the question, what is an interesting "thing" to learn? Maybe it's:
Detecting cancer
Predicting the outcome between two sports teams
Filtering spam
Detecting faces
Reading text (OCR)
Playing a game
The sky is the limit, really!
Since it has a business tie in - given some input set determine probable business fraud from the input (something the SEC seems challenged in doing). We now have several examples (Madoff and others). Or a system to estimate investment risk (there are lots of such systems apparently but were any accurate in the case of Lehman for example).
A starting point might be the Chen book Genetic Algorithms and Genetic Programming in Computational Finance.
Here's an AAAI writeup of an award to the National Association of Securities Dealers for a system thatmonitors NASDAQ insider trading.
Many great answers posted already, but I wanted to add my 2 cents.There is one hot topic in which big companies all around are investing lots of resources into, and is still a very challenging topic with lots of potential: Automated detection of fake news.
This is even more relevant nowadays where most of us are connecting though social media and there's a huge crisis looming over.
Fake news, content removal, source reliability... The problem is huge and very exciting. It is as I said challenging as it can be seen from many perspectives (from analising images to detect fakes using adversarial netwotks to detecting fake written news based on text content (NLP) or using graph theory to find sources) and the possbilities for a research proyect are endless.
I suggest you read some general articles (e.g this or this) or have a look at research articles from the last couple of years (a quick google seach will throw you a lot of related stuff).
I wish I had the opportunity of starting over a project based on this topic. I think it's going to be of the upmost relevance in the next few years.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 6 years ago.
Improve this question
Our brain consists of billions of neurons which basically work with all the incoming data from our senses, handle our consciousness, emotions and creativity as well as our hormone system, etc.
So I'm completely new to this topic but doesn't each neuron have a fixed function? E.g.: If a signal of strength x enters, if the last signal was x ms ago, redirect it.
From what I've learned in biology about our nerves system which includes our brain because both consist of simple neurons, it seems to me as our brain is one big, complicated computer.
Maybe so complicated that things such as intelligence and cognition become possible?
As the most complicated things about a neuron pretty much are the chemical aspects on generating an electric singal, keeping itself alive, and eventually segmenting itself, it should be pretty easy emulating some on a computer, or?
You won't have to worry about keeping your virtual neuron alive, or?
If you can emulate a single neuron on a computer, which shouldn't be too hard, could you theoretically emulate more than 1000 billions of them, recreating intelligence, cognition and maybe even creativity?
In my question I'm leaving out the following aspects:
Speed of our current (super) computers
Actually writing a program for emulating neurons
I don't know much about this topic, please tell me if I got anything wrong :)
(My secret goal: Make a copy of my brain and store it on some 10 million TB HDD and make someone start it up in the future)
A neuron-like circuit can be built with a handful of transistors. Let's say it takes about a dozen transistors on average. (See http://diwww.epfl.ch/lami/team/vschaik/eap/neurons.html for an example.)
A brain-sized circuit would require 100 billion such neurons (more or less).
That's 1.2 trillion transistors.
A quad-core Itanium has 2 billion transistors.
You'd need a server rack with 600 quad-core processors to be brain-sized. Think $15M US to purchase the servers. You'll need power management and cooling plus real-estate to support this mess.
One significant issue in simulating the brain is scale. The actual brain only dissipates a few watts. Power consumption is 3 square meals per day. A pint of gin. Maintenance is 8 hours of downtime. Real estate is a 42-foot sailboat (22 Net Tons of volume as ships are measured) and a place to drop the hook.
A server cage with 600 quad-core processors uses a lot more energy, cooling and maintenance. It would require two full-time people to keep this "brain-sized" server farm running.
It seems simpler to just teach the two people what you know and skip the hardware investment.
Roger Penrose presents the argument that human consciousness is non-algorithmic, and thus is not capable of being modeled by a conventional Turing machine-type of digital computer. If it's like that you can forget about building a brain with a computer...
Simulating a neuron is possible and therefore theoretically simulating a brain is possible.
The two things that always stump me as an issue is input and output though.
We have a very large number of nerve endings that all provide input to the brain. Without them the brain is useless. How can we simulate something as complicated as the human brain without also simulating the entire human body!?!
Output, once the brain has "dealt" with all of the inputs that it gets, what is then the output from it? How could you say that the "copy" of your brain was actually you without again hooking it up to a real human body that could speak and tell you?
All in all, a fascinating subject!!!!
The key problem with simulating neural networks (and human brain is a neural network) is that they function continuously, while digital computers function in cycles. So in a neural network different neurons function independently in parallel while in a computer you only simulate discrete system states.
That's why adequately simulating real neural networks is very problematic at the moment and we're very far from it.
Yes, the Blue Brain Project is getting close, and I believe Moore's Law has a $1000 computer getting there by 2049.
The main issue is that our brains are based largely on controlling a human body, which means that our language comprehension and production, the basis of our high-level reasoning and semantic object recognition, is strongly tied to its potential and practiced outputs to a larynx, tongue, and face muscles. Further, our reward systems are tied to signals that indicate sustenance and social approval, which are not the goals we generally want a brain-based AI to have.
An exact simulation of the human brain will be useful in studying the effects of drugs and other chemicals, but I think that the next steps will be in isolating pathways that let us do things that are hard for computers (e.g. visual system, fusiform gyrus, face recognition), and developing new or modifying known structures for representing concepts.
Short: yes we will surely be able to reproduce artificial brains, but no it maybe won't be with our current computers models (Turing machines), because we simply don't know yet enough about the brain to know if we need new computers (super-Turing or biologically engineered brains) or if current computers (with more power/storage space) are enough to simulate a whole brain.
Long:
Disclaimer: I am working in computational neuroscience research and I am interested both by the neurobiological side and the computational (artificial intelligence) side.
Most of the answers assume as true OP's postulate that simulating neurons is enough to save the whole brain state and thus simulate a whole brain.
That's not true.
The brain is more than just neurons.
First, there is the connectivity, the synapses, that is of paramount importance, even maybe more than neurons.
Secondly, there are glial cells such as astrocytes and oligodendrocytes that also possess their own connectivity and communication system.
Thirdly, neurons are heterogenous, which means that there is not just one template model of a neuron that we could just scale up to the required amount to simulate a brain, we also have to define multiple types of neurons and place them pertinently at the right places. Plus, the types can be continuous, so in fact you can have neurons that are half way between 3 different types...
Fourthly, we don't know much about the rules of brain's information processing and management. Sure, we discovered that the cerebellum works pretty much like an artificial neural network using stochastic gradient descent, and that the dopaminergic system works like TD-learning, but then we have no clue about the rest of the brain, even memory is out of reach (although we guess it's something close to a Hopfield network, but there's no precise model yet).
Fifthly, there are so many other examples from current research in neurobiology and computational neuroscience showing the complexity of brain's objects and networks dynamics that this list can go on and on.
So in the end, your question cannot be answered, because we simply do not know yet enough about the brain to know if our current computers (Turing machines) are enough to reproduce the complexity of biological brains to give rise to the full spectrum of cognitive functions.
However, biology field is getting closer and closer to computer science field, as you can see with biologically engineered viruses and cells that are programmed pretty much like you develop a computer program, and genetical therapies that basically re-engineer a living system based on its "class" template (the genome). So I dare to say that once we know enough about the brain's architecture and dynamics, the in-silico reproduction won't be an issue: if our current computers cannot reproduce the brain because of theoretical constraints, we will devise new computers. And if only biological systems can reproduce the brain, we will be able to program an artificial biological brain (we can already 3D-print functional bladders and skin and veins and hearts etc.).
So I would dare say (even if it can be controversial, this is here my own claim) that yes, artificial brains will surely be possible someday, but whether it will be as a Turing machine computer, a super-Turing computer or a biologically engineered brain remain to be seen depending on our progress in the knowledge of brain's mechanisms.
I don't think they are remotely close enough to understanding the human brain to even begin thinking about replicating it.
Scientists would have you think we are nearly there, but with regards to the brain we're not much further along than Dr. Frankenstein.
What is your goal? Do you want a program that can make intelligent decisions or a program that provides a realistic model of how the human brain actually works? Artificial intelligence can be approached from the perspective of psychology, where the goal is to simulate the brain and thereby get a better understanding of how humans think, or from the perspective of mathematics, optimization theory, decision theory, information theory, and computer science, in which case the goal is to create a program that is capable of making intelligent decisions in a computationally efficient manner. The latter, I would say is pretty much solved, although advances are definitely still being made. When it comes to a realistic simulation of the brain, I think we were only recently able to simulate a brain of cat semi-realistically; when it comes to humans, it would not be very computationally feasible at present.
Researchers far smarter than most recon so, see Blue Brain from IBM and others.
The Blue Brain Project is the first
comprehensive attempt to
reverse-engineer the mammalian brain,
in order to understand brain function
and dysfunction through detailed
simulations.
Theoretically the brain can be modeled using a computer (as software and hard/wetware are compatible or mutually expressible). The question isn't a theoretical one as far as computer science goes, but a philosophical one:
Can we model the (chaotic) way in which a brain develops. Is a brains power it's hardware or the environment that shapes the development and emergent properties of that hardware as it learns
Even more mental:
If I, with 100% accuracy modeled my own brain, then started the simulation. And that brain had my memories (as it has my brain's physical form) ... is it me? If not, what do I have that it doesn't?
I think that if we are ever in a position to emulate the brain, we should have been working on logical system based on biological principles with better applications than the brain itself.
We all have a brain, and we all have access to it's amazing power already ;)
A word of caution. Current projects on brain simulation work on a model of a human brain. Your idea about storing your mind on a hard-disk is crazy: if you want a replica of your mind you'll need two things. First, another "blank" brain. Second, devise a method to perfectly transfer all the information contained in your brain: down to the quantum states of every atom in it.
Good luck with that :)
EDIT: The dog ate part of my text.
I was wondering if you creative minds out there could think of some situations or applications in the web environment where Neural Networks would be suitable or an interesting spin.
Edit: Some great ideas here. I was thinking more web centric. Maybe bot detectors or AI in games.
To name a few:
Any type of recommendation system (whether it's movies, books, or targeted advertisement)
Systems where you want to adapt behaviour to user preferences (spam detection, for example)
Recognition tasks (intrusion detection)
Computer Vision oriented tasks (image classification for search engines and indexers, specific objects detection)
Natural Language Processing tasks (document/article classification, again search engines and the like)
The game located at 20q.net is one of my favorite web-based neural networks. You could adapt this idea to create a learning system that knows how to play a simple game and slowly learns how to beat humans at it. As it plays human opponents, it records data on game situations, the actions taken, and whether or not the NN won the game. Every time it plays, win or lose, it gets a little better. (Note: don't try this with too simple of a game like checkers, an overly simple game can have every possible game/combination of moves pre-computed which defeats the purpose of using the NN).
Any sort of classification system based on multiple criteria might be worth looking at. I have heard of some company developing a NN that looks at employee records and determines which ones are the least satisfied or the most likely to quit.
Neural networks are also good for doing certain types of language processing, including OCR or converting text to speech. Try creating a system that can decipher capchas, either from the graphical representation or the audio representation.
If you screen scrap or accept other sites item sales info for price comparison, NN can be used to flag possible errors in the item description for a human to then eyeball.
Often, as one example, computer hardware descriptions are wrong in what capacity, speed, features that are portrayed. Your NN will learn that generally a Video card should not contain a "Raid 10" string. If there is a trend to add Raid to GPUs then your NN will learn this over time by the eyeball-er accepting an advert to teach the NN this is now a new class of hardware.
This hardware example can be extended to other industries.
Web advertising based on consumer choice prediction
Forecasting of user's Web browsing direction in micro-scale and very short term (current session). This idea is quite similar, a generalisation, to the first one. A user browsing Web could be proposed with suggestions with other potentially interesting websites. The suggestions could be relevance-ranked according to prediction calculated in real-time during user's activity. For instance, a list of proposed links or categories or tags could be displayed in form of a cloud and font size indicates rank score. Each and every click a user makes is an input to the forecasting system, so the forecast is being constantly refined to provide user with as much accurate suggestions, in terms of match against user's interest, as possible.
Ignoring the "Common web problems" angle request but rather "interesting spin" view.
One of the many ways that a NN can be viewed/configured, is as a giant self adjusting, multi-input, multi-output kind of case flow control.
So when you want to offer match ups that are fuzzy, (not to be confused directly with fuzzy logic per se, which is another area of maths/computing) NN may offer a usable alternative.
So to save energy, you offer a lift club site, one-offs or regular trips. People enter where they are, where they want to go and at what time. Sort by city and display in browse control.
Using a NN you could, over time, offer transport owners to transport seekers by watching what owners and seekers link up. As a owner may not live in the same suburb that a seeker resides. The NN learns over time what variances in owners, seekers physical location difference appear to be acceptable. So it can then expand its search area when offering a seekers potential owners.
An idea.
Search! Recognize! Classify! Basically everything search engines do nowadays could benefit from a dose of neural networks and fuzzy logic. This applies in particular to multimedia content (e.g. content-indexing images and videos) since that's where current search technologies are lagging behind.
One thing that always amazes me is that we still don't have any pseudo-intelligent firewalling technology. Something that says "hey his range of urls is making too much requests when they are not supposed to", blocks them, and sends a report to an administrator. That could be done with a neural network.
On the nasty part of things, some virus makers could find lucrative uses to neural networks. Adaptative trojans that "recognized" credit card numbers on a hard drive (instead of looking for certain cookies) or that "learn" how to mask themselves from detectors automatically.
I've been having fun trying to implement a bot based on a neural net for the Diplomacy board game, interacting via DAIDE protocols. It turns out to be extremely tricky, so I've turned to XCS to simplify the problem.
Suppose EBay used neural nets to predict how likely a particular item was to sell; predict what the best day to list items of that type would be, suggest a starting price or "buy it now price"; or grade your description based on how likely it was to attract buyers? All of those could be useful features, if they worked well enough.
Neural net applications are great for representing discrete choices and the whole behavior of how an individual acts (or how groups of individuals act) when mucking around on the web.
Take news reading for instance:
Back in the olden days, you picked up usually one newspaper (a choice), picked a section (a choice), scanned a page and chose an article (a choice), and read the basics or the entire article (another choice).
Now you choose which news site to visit and continue as above, but now you can drop one paper, pick up another, click on ads, change sections, and keep going with few limits.
The whole use of the web and the choices people make based on their demographics, interests, experience, politics, time of day, location, etc. is a very rich area for NN application. This is especially relevant to news organizations, web page design, ad revenue, and may even be an under explored area.
Of course, it's very hard to predict what one person will do, but put 10,000 of them that are the same age, income, gender, time of day, etc. together and you might be able to predict behavior that will lead to better designs. Imagine a newspaper (or even a game) that could be scaled to people's needs based on demographics. An ad man's dream !
How about connecting users to the closest DNS, and making sure there are as few bounces as possible between the request and the destination?
Friend recommendation in social apps (Linkedin,facebook,etc)