Graph Neural Networks can be a game changer in Machine Learning!

Happy new year! As new year comes, I’m thinking about what to do about AI this year. After exploring various things, I decide to concentrate on “Graph Neural Networks” in 2022. I’ve heard the name “Graph Neural Networks” before, but since the success stories have been reported in several applications last year, I think it is the right time to work on it in 2022.

Graph is often represented by a diagram connecting dots, just like this.

Dots are called “nodes” and there are “edges” between nodes. They are very important in “Graph Neural Networks” or “GNN” in short.

These can be expressed intuitively with Graph. So they can be analysed by GNN.

• Social network
• Molecular structure of the drug
• Structure of the brain
• Transportation system
• Communications system

If you have a structure that emphasizes relationships between nodes or dots, you can express it in Graph and use GNN for analysis. Due to its complexity, GNN hasn’t appeared much as an AI application, but in last year, I think we’ve seen a lot of success results. It seems that the number of papers on GNN published is increasing steadily.

In August of last year, DeepMind and Google researchers released that they predicted the arrival time at the destination using Google Map data and improved the accuracy. The roads were graphed by segment and analyzed using “Graph Neural Networks”. The structure of the model itself seems to be unexpectedly simple. For details, please see 3.2 Model Architecture in the research paper (1).

There are many other successful cases. Especially in the field of drug discovery, it seems to be expected.

Theoretically, “Graph Neural Networks” is a fairly broad concept and seems to have various models. The theoretical framework is also deepening with the participation of leading researchers, and research is likely to accelerate further in 2022.

So, “Graph Neural Networks” is a very interesting to me. When I find good examples, I would like to update it here. Stay tuned!

１）ETA Prediction with Graph Neural Networks in Google Maps, 25 Aug 2021

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software

“Monte Carlo tree search ” is the key in AlphaGo Zero!

On October last year, Google DeepMind released “AlphaGo Zero“.  It is stronger than all previous versions of Alpha Go although this new version uses no human knowledge of Go for training. It performs self-play and gets stronger by itself.  I was very surprised to hear the news. Because we need many data to train the model in general.

Today, I would like to consider why AlphaGo Zero works well from the viewpoint of Go-player as I played it for entertainment purpose so many years. I am not a Profesional Go player. But I have the expertise of both Go and Deep learning.  So it is a good opportunity for me to consider it now.

When I play Go,  I make decisions for next move based on the intuition in many cases because I am very confident that “it is right’. But when we are in a more complex situation in Go and are not so sure what the best move is, I should try many paths that I and my opponent can take each turn in my mind (not move on the real board) and want to choose the best move based on trials.  We call it “Yomi” in Japanese.  Unfortunately, I sometimes perform “Yomi” wrongly, then I make a wrong decision to move. Professional Go players perform “Yomi” much more accurately than I do.  This is the key to be strong players in Go.

 

Then I wonder how AlphaGo Zero can perform “Yomi” effectively.  I think this is the key to understand AlphaGo Zero. Let me consider these points

 

1.Monte Carlo tree search (MCTS) performs “Yomi” effectively.

Next move can be decided by the policy/value function. But there might be another better move. So we need to search for it. MCTS is used for this search in AlphaGo Zero. Based on the paper, MCTS can find the better move that original move was chosen by the policy/value function.  DeepMind says MCTS works as “powerful policy improvement operator” and “improved MCTS-based policy” can be obtained. This is great as it means that AlphaGo Zero can perform “Yomi” just like us.

 

2. A game can be continued by Self-play without human knowledge.

I wonder how we can play a whole game of Go without human knowledge. The paper explains it as follows    “Self-play with search—using the improved MCTS-based policy to select each move, then using the game-winner z as a sample of the value—may be viewed as a powerful policy evaluation operator.”  So just playing games with itself,  the winner of the game can be obtained as a sample. These results are used for next learning processes. Therefore ”Yomi” by AlphaGo Zero can be more accurate.

 

 

3. This training algorithm is very efficient to learn from scratch

Computers are very good at performing simulations so many times automatically.  So without human knowledge in advance, AlphaGo Zero can be stronger and stronger when it does “self-play” so many times. Based on the paper, starting with random play, AlphaGo Zero outperformed the previous version of AlphaGo that beat Lee Sedol in March 2016,  just after 72 hours training. This is incredible because it is required only 72 hours to develop the model to beat professional players from scratch without human knowledge.

 

 

Overall, AlphaGo Zero is incredible. If AlphaGo Zero training algorithm can be applied to our businesses,  AI professional-businessman might be created in 72 hours without human knowledge. This must be incredibly sophisticated!

Hope you enjoy the story of how AlphaGo Zero works. This time I overview the mechanism of AlpahGo Zero.  When you are interested in it more details, I recommend watching the video by DeepMind. In my next article, I would like to go a little deeper into MCTS and training of models.  It must be exciting!  See you again soon!

 

Mastering the game of Go without human knowledge by DeepMind

David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, Yutian Chen, Timothy Lillicrap, Fan Hui, Laurent Sifre, George van den Driessche, Thore Graepel & Demis Hassabis

Published in NATURE, VOL 550, 19 OCTOBER 2017

Notice: TOSHI STATS SDN. BHD. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithm or ideas contained herein, or acting or refraining from acting as a result of such use. TOSHI STATS SDN. BHD. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on TOSHI STATS SDN. BHD. and me to correct any errors or defects in the codes and the software.

Is this a real voice by human being? It is amazing as generated by computers

As I shared the article this week,  I found the exciting system to generate voices by computers. When I heard the voice I was very surprised as it sounds so real. I recommend you to listen to them in the website here.  There are versions of English and Mandarine. This is created by DeepMind, which is one of the best research arms of artificial intelligence in the world. What makes it happen?   Let us see it now.

 

1. Computers learns our voices deeper and deeper

According to the explanation of DeepMind, they use “WaveNet, a deep neural network for generating raw audio waveforms”.  They also explain”pixel RNN and pixel CNN”, which are invented by them earlier this year. (They have got one of best paper award at ICML 2016, which are one of the biggest international conference about machine learning, based on the research). By applying pixel RNN and CNN to voice generation, computers can learn wave of voices far more details than previous methods. It enables computers generate more natural voices. It is how WaveNet is born this time.

As the result of learning raw audio waveforms, computer can generate voices that sound so real. Could you see the metrics below?  The score of WaveNet is not so different from the score of Human Speech (1). It is amazing!

2. Computers can generate man’s voice as well as woman’s voice at the same time

As computer can learn wave of our voices more details,  they can create both man’s voice and woman’s voice. You can also listen to each of them in the web. DeepMind says “Similarly, we could provide additional inputs to the model, such as emotions or accents”(2) . I would like to listen them, too!

 

3. Computers can generate not only voice but also music!

In addition to that,  WaveNet can create music, too.  I listen to the piano music by WaveNet and I like it very much as it sounds so real. You can try it in the web, too.  When we consider music and voice as just data of audio waveforms, it is natural that WaveNets can generate not only voices but also music.

 

If we can use WaveNet in digital marketing, it must be awesome! Every promotions, instructions and guidance to customers can be done by voice of  WaveNet!  Customers may not recognize “it is the voice by computers”.  Background music could be optimized to each customer by WaveNet, too!  In my view, this algorithm could be applied to many other problems such as detections of cyber security attack, anomaly detections of vibrations of engines, analysis of earthquake as long as data can form  of “wave”.  I want to try many things by myself!

Could you listen the voice by WaveNet? I believe that in near future, computers could learn how I speech and generate my voice just as I say.  It must be exciting!

 

 

1,2.  WaveNet:A generative model for Raw Audio

https://deepmind.com/blog/wavenet-generative-model-raw-audio/

 

 

Notice: TOSHI STATS SDN. BHD. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithm or ideas contained herein, or acting or refraining from acting as a result of such use. TOSHI STATS SDN. BHD. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on TOSHI STATS SDN. BHD. and me to correct any errors or defects in the codes and the software

We might need less energy as artificial intelligence can enable us to do so

When I heard the news about the reduction of consumption energy in google data center (1), I was very surprised.  Because it has been optimized for a long time. It means that it is very difficult to improve the efficiency of the system more.

It is done by “Google DeepMind“, which has been developing “General artificial intelligence”. Google DeepMind is an expert on “deep learning‘. It is one of major technologies of artificial intelligence. Their deep learning models can reduce the energy consumption in data center of google dramatically.  Many data are corrected in data center, — data such as temperatures, power, pump speeds, etc. — and the models provide more efficient control of energy consumption. This is amazing. If you are interested in the details, you can read their own blog from the link below.

 

It is easy to imagine that there are much room to get more efficiency outside google data centers. There are many huge systems such as factories, airport, power generators, hospitals, schools, shopping mall, etc.. But few systems could have the same control as Google DeepMind provides. I think they can be more effeicent based on the points below.

1.More data will be available from devices, sensors and social media

Most people  have their own mobile devices and use them everyday.  Sensors are getting cheaper and there are many sensors in factories, engines on airplanes and automobile, power generations,etc. People use social media and generate their own contents everyday. It means that massive amount of data are generating and volume of data are increasing dramatically. The more data are available, the more chances we can get to improve energy consumptions.

 

2. Computing resources are available from anywhere and anytime

The data itself can say nothing without analyzing it.  When massive amount of data is available,  massive amount of computer resources are needed. But do not worry about that. Now we have cloud systems. Without buying our own computer resources, such as servers, we can start analyzing data with “cloud“.  Cloud introduces “Pay as you go” system. It means that we do not need huge initial investments to start understanding data. Just start it today with cloud.  Cloud providers, such as Amazon web service, Microsoft Azure and Google Cloud Platform, prepare massive amount of computer resources which are available for us.  Fast computational resources, such as GPU (Graphics processing unit) are also available. So we can make most out of massive amount of data.

 

3. Algorithms will be improved at astonishing speed.

I have heard that there are more than 1000 research papers to submit and apply to one major machine learning international conference. It means that many researchers are developing their own models to improve the algorithms everyday. There are many international conferences on machine learning every year. I can not imagine how many innovations of algorithms will appear in future.

 

At the end of their blog, Google DeepMind says

“We are planning to roll out this system more broadly and will share how we did it in an upcoming publication, so that other data centre and industrial system operators — and ultimately the environment — can benefit from this major step forward.”

So let us see what they say in next publication.  Then we can discuss how to apply their technology to our own problems. It must be exciting!

 

 

(1) DeepMind AI Reduces Google data center cooling bill by 40%,  21st July 2016

https://deepmind.com/blog

 

 

Notice: TOSHI STATS SDN. BHD. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithm or ideas contained herein, or acting or refraining from acting as a result of such use. TOSHI STATS SDN. BHD. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on TOSHI STATS SDN. BHD. and me to correct any errors or defects in the codes and the software

Will the self-driving cars come to us in 2020?

Since last year, the progress of development of self-driving cars are accelerated rapidly.  When I wrote about it last year, someone may not be convinced that the self-driving cars come true. But now no one can doubt about self-driving cars anymore. The problem is when it comes in front of us.  I would like to consider several key points to develop the technology of self-driving cars.

 

1.Data from experiments

It is key to develop self-driving car effectively. Because self-driving cars need artificial intelligence in it to drive cars by themselves without human interventions. As you know, artificial intelligence looks like our brains.  When we are born, our brain is almost empty. But as we grow, we can learn many things through our experiences.  This is the same for artificial intelligence. It needs massive amounts of data to learn. Recently, Google and  Fiat Chrysler Automobiles NV announced that they cooperate to enhance development of self-driving cars. According to the article on Bloomberg, “The carmaker plans to develop about 100 self-driving prototypes based on the Chrysler Pacifica hybrid-powered minivan that will be used by Google to test its self-driving technology.”(1)  The more cars are used in the experiments, the more data they can obtain. Therefore, it enables Google to accelerate to develop self-driving cars more rapidly.

 

2. Algorithm of artificial intelligence

With data from experiments, artificial intelligence will be more sophisticated.  The algorithms of artificial intelligence, which are called “Deep Learning” should be more effective from now.  Because driving cars generates sequences of data and need sequential decision making processes, such as stop, go, turn right, accelerate, and so on,  we need algorithms which can handle these situations. In my view, the combination of deep learning and reinforcement learning can be useful to do that.  This kind of technologies is developed in research centers, such as Google DeepMind which is famous for the artificial intelligence Go player. It says this technology can be used for robotics, medical research and economics.  So why not for self-driving cars?

 

3. Interactions with human drivers

It seems to be very difficult to decide who is responsible for driving cars.  Initially, self-driving cars might appear with the handle and brakes. It means that human can intervene the operations of self-driving cars. When accidents happen,  who is responsible?  Human or machines?  When self-driving cars without handle and brakes are available,  machines are responsible as human can not control cars anymore. So the machines are 100% responsible for accidents. It is very difficult to decide which is better, self-driving cars with and without handle and breaks. It depends on the development of technologies and regulations.

 

Impact on society is huge when self-driving cars are introduced to us.  Bus, Taxi, Track could be replaced with self-driving cars.  Not only drivers but also road maintenance  companies, car insurance companies, roadside shops, traffic light makers, railway companies, highway running companies,  car maintenance companies and car parking providers are also heavily impacted. Government should consider how we can implement self-driving cars to our societies effectively. I do not think we have spare time to consider it. Let us start it today!

 

(1) http://www.bloomberg.com/news/articles/2016-05-03/fiat-google-said-to-plan-partnership-on-self-driving-minivans

 

Note: Toshifumi Kuga’s opinions and analyses are personal views and are intended to be for informational purposes and general interest only and should not be construed as individual investment advice or solicitation to buy, sell or hold any security or to adopt any investment strategy.  The information in this article is rendered as at publication date and may change without notice and it is not intended as a complete analysis of every material fact regarding any country, region market or investment.

Data from third-party sources may have been used in the preparation of this material and I, Author of the article has not independently verified, validated such data. I accept no liability whatsoever for any loss arising from the use of this information and relies upon the comments, opinions and analyses in the material is at the sole discretion of the user. 

Will the age of “Brain as a Service” come to us in near future?

15 March 2016,  I found two things which may change the world in the future,  The former, artificial intelligence Go player “AlphaGo” and the latter is an automated marketing system “Google Analytics 360 Suite“. Both of them came from Google. Let me explain why I think the age of “Brain as a service” is coming  based on these two innovations.

1. AlphaGo

You may know what AlphaGo achieved on 15 March 2016.  At  Google DeepMind Challenge, where artificial intelligence Go player had five games against a top professional Go player. It beats Lee sedol, who is one of the strongest Go player in the world, 4 to 1.  Go is one of the oldest games, which are mainly played in China, Korea, Japan and Taiwan. At the beginning of the challenge, few people thought AlphaGo could win the games as it is always said that  Go is so complex that computers can not win professional Go players at least in 10 years. The result was, however, completely opposite. Therefore,  other professional Go players, artificial intelligence researchers and even people who do not play Go must be upset to hear the news. AlfaGo is strengthened by algorithms, which are called “deep learning” and “reinforcement learning“. It can learn the massive amount of Go patterns created by human being for a long time.  Therefore, we need not to program specifically, one by one as computers can learn by themselves. It looks like our brains. We are born without any knowledge and start learning many things as we grow.  Finally, we can be sophisticated enough to be “adult”. Yes, we can see “AlphaGo” as a brain.  It can learn by itself at an astonishing speed as it does not need to rest.  It is highly likely that Google will use this brain to improve many products in it in the future.

 

2. Google Analytics 360 Suite

Data is a king.  But it is very difficult to feed them into computers effectively.  Some data are stored in servers. Others are stored in local PCs. No one knows how we can well-organize data effectively to obtain the insights from data.  Google is strong for consumer use.  G-mails, Android and google search are initially very popular among consumers. But the situations are gradually changing.  Data and algorithms have no-boarders between consumers and enterprises. So it is natural for Google to try to obtain enterprise market more and more. One of the examples is  “Google analytics 360 Suites”. Although I never tried it yet, this is very interesting for me because it can work as a perfect interface to customers. Customers may request many things, ask questions and make complains to your services. It is very difficult to gather these data effectively when systems are not united seamlessly. But with “Google analytics 360 Suites”,  data of customers could be tracked in a timely manner effectively.  For example, the data from Google analytics 360 may be going to Google Audience Center 360,  which is a data management platform (DMP).  It means that the data is available to any analyses that marketers want.  “Google Audience Center 360” can collect data from other sources or third party data providers. It means that many kind of data could be ready to be fed into computers effectively.

 

3. Data is gasoline for “Artificial intelligence”

AlfaGo can be considered as “Artificial intelligence”. “Artificial intelligence” is like our brain.  There is no knowledge in it initially.  It has only structures to learn.  In order to be “intelligent”, it should learn a lot from data. It means that massive amount data should be fed into computers. Without data, “artificial intelligence” can do nothing. Now data management like “Google Audience Center 360” is in progress. It seems that data are getting well organized to be fed into computers.  The centralized data management system can collect data automatically from many systems. It becomes easier to feed massive amounts of data into computers. It enables to computers learn the massive amount of data. These things must be a trigger to change the landscape of our business, societies and lives. Because suddenly computers can be sophisticated enough to work just like our brain.  AlphaGo teaches us that it may happen when a few people think so. Yes, this is why I think that the age of “Brain as a Service” will come in near future.  How do you think of that?

 

 

Note: Toshifumi Kuga’s opinions and analyses are personal views and are intended to be for informational purposes and general interest only and should not be construed as individual investment advice or solicitation to buy, sell or hold any security or to adopt any investment strategy.  The information in this article is rendered as at publication date and may change without notice and it is not intended as a complete analysis of every material fact regarding any country, region market or investment.

Data from third-party sources may have been used in the preparation of this material and I, Author of the article has not independently verified, validated such data. I and TOSHI STATS.SDN.BHD. accept no liability whatsoever for any loss arising from the use of this information and relies upon the comments, opinions and analyses in the material is at the sole discretion of the user. 

 

Can you win Atari games against computers? It seems to be impossible anymore

I think it is better to watch the youtube of interview here first. Onstage at TED2014, Charlie Rose interviews Google CEO Larry Page about his far-off vision for the company.  Page talks through the company’s recent acquisition of Deep Mind, an AI that is learning some surprising.  At the time of 2 minutes 30 seconds in his interview,  he talks about DeepMind for two minutes.

 

According to white paper from DeepMind which were bought by Google at 650m USD in Jan 2014,  in three games of Atari 2600, Breakout, Enduro, Pong,  human can not win against computers after computer learns how each game works for a couple of hours.  There is only one same program prepared for each game and there is no input about how to win the specific game in advance.  It means that only one program should learn how to obtain high score from scratch by itself.  At the result of six games,  computers could record higher score than human experts in three games. It is amazing.

Reinforcement learning, one of machine learning, is used in this challenge. It is different form machine learning used in image recognition and natural language processing.  In reinforcement learning,  reward functions are used to decide what the best policy among many choices in the long run.  We can say in short “how much we should give up today’s lunch,  in order to maximize total sum of lunches tomorrow and later”. We always face this kind of problems but it is difficult for computers to answer.  However DeepMind proved reinforcement learning works well against this kind of problems when they presented the demo at the end of 2013.

 

If this kind of decision-making is available by computers, it will give huge impacts to intellectual jobs, such as lawyers, fund managers, analysts and cooperate officers because they make decisions in long-term horizon, rather than outcomes in tomorrow. They have a lot of experiences in the past, some of  them are successes and others are failures, they can use these experiences when they make a plan for the future.  If computers can use same logic as human and make decisions by themselves, it can be a revolution for intelligent job.  For example, at board meetings in companies, computers may answer questions about management strategies from board members based on the massive amount of past examples and tell them how to maximize future cash flow by using reinforcement learning.  Future cash flow is the most important thing to board members because share holders require to maximize it.

 

Currently a lot of discussions about our future jobs are going on because it is probable that many jobs will be replaced by computers in near future. If reinforcement learning have been improved, CEO of companies might be replaced by computers and share holders might welcome for them in future ?!