Saturday, 7 May 2022

Abortion Laws and Fertility Rates

 

Abortion Laws and Fertility Rates

I generally try to stay away from highly political subjects, but as a data scientist (who sometimes has to do a bit of demographic analysis) I can’t help observing patterns in data that might help to explain events in the world, to myself if to nobody else.

Here’s a pattern that I think helps explain why the Roe vs Wade (abortion rights) issue has re-emerged in the United States this. I say re-emerge, though obviously this issue has never been far from the forefront of the political battlefield. However, the Supreme Court has taken up the issue again, after being mostly unwilling to touch it, after 50 years. Why is that?

Well obviously, there have been changes in the makeup of the Supreme Court recently which have shifted the balance of the membership to a more restrictive stance (or so it is assumed). But, the membership of the court has always been in flux and has had right-leaning majorities at other times in the past five decades. So, what else has changed?

Here is where the graph shown above comes into the picture. It takes a global view of the relationship between abortion laws and fertility rates, at a country-by-country level. 

Abortion laws have been rated by the degree to which they restrict rights to abortion. Completed fertility rates indicate the average number of children a woman is expected to have over her lifetime, given current trends in any given country. (Detailed data and sources for the data are given at the end of the blog.)

The graph shows that there is a clear association between abortion rights and completed fertility rates. Countries with more restrictive laws tend to have higher fertility rates, while those with less restrictive laws have lower fertility rates.

That’s not to say that this is a cause and effect relationship – it is more likely correlational. It isn’t necessarily that more liberal abortion laws lead to more abortions, which lead to a lower birth rate. That is probably far too simplistic. (In fact there has been some research showing that the reverse is often true, as women who have an abortion often stop at one child).

It is more a matter of what economists refer to as “nudges” or what political scientists would likely call signalling from the wider public culture. The relative strictness of abortion laws within a society sends a signal about the value that is placed on family formation and reproduction by that society. That signal is, of course, tangled up within a mesh of other cultural aspects, such as religion, economics and cultural traditions and standards. The same is true of matters such as public support for daycare and other efforts to make life-work balance more amenable to child-rearing in general.


Why would this be happening now? The second graph helps to explain that. As you can see nearly two-thirds of the world’s population are now living in relatively low fertility countries, with nearly four-tenths living in below replacement fertility countries (replacement fertility is conventionally estimated to be about 2.1). So, at the global level, the ratio of population sources to population sinks is shifting. That means that using immigration to drive population policies will become less and less tenable.

Along with that, other phenomena are showing the limits of globalization theory. For example:

  • Pandemics are more likely when travel and trade is relatively unrestricted.

  • The fragility of complex world-wide supply-chains is being revealed, partly from the Covid pandemic and partly from geopolitical conflict, such as the situation in Ukraine.

  • The impact of population policies on global warming will become more and more urgent.

  • Countries may be less and less willing to allow emigration, especially of their brightest and best educated. There may come an expectation that they should stay home and help their native land to develop. “Poaching” these highly skilled people may even become seen to be immoral, a new form of human resource colonialism.

I am inclined to believe that demographic issues will become more and more contested in the near future, especially in the lower fertility countries. The re-opening of Roe vs Wade is likely just an early phase in this development. Sometimes efforts to address these matters will be cast in what are conventionally considered conservative terms (e.g. stricter abortion laws), sometimes in what are conventionally considered liberal terms (e.g. more public funding for early childcare). Often the demographic realities underlying the policies will be downplayed or ignored, as there is a sort of taboo about these issues, though I think those taboos will dissipate in the near future. Demographic realities pretty well demand that.

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



There are two sources for the graph data, which are given below.

The x-axis is a categorization of countries by how restrictive their abortion laws currently are. The data is from the group “Center for Reproductive Rights”. The categorizations are given below.

Category I. Prohibited Altogether (24 countries)

Category II. To Save the Woman’s Life (43 countries)

Category III. To Preserve Health (53 countries)

Category IV. Socioeconomic Grounds (13 countries)

Category V. On Request (Gestational Limits Vary) (75 countries)

website: https://reproductiverights.org/maps/worlds-abortion-laws/

The y-axis is from the website of the organization World Population Review, which has statistics on both population and completed fertility rates.

https://worldpopulationreview.com/country-rankings/total-fertility-rate

For completeness here are graphs using unweighted means and medians for the fertility measures.



And here is a detailed list of countries used for the graphs, with Abortion Law categorizations, fertility rates and populations by country.

LawCateg

CountryLaw

Median - fertilityRate

Average - fertilityRate

Sum - Population

1

Andorra

1.30

1.30

77,463


Aruba



107,609


Congo (Brazzaville)

4.40

4.40

5,797,805


Curaçao



165,529


Dominican Republic

2.30

2.30

11,056,370


Egypt

3.30

3.30

106,156,692


El Salvador

2.00

2.00

6,550,389


Haiti

2.90

2.90

11,680,283


Honduras

2.50

2.50

10,221,247


Iraq

3.70

3.70

42,164,965


Jamaica

2.00

2.00

2,985,094


Laos

2.70

2.70

7,481,023


Madagascar

4.10

4.10

29,178,077


Malta

1.20

1.20

444,033


Mauritania

4.60

4.60

4,901,981


Nicaragua

1.70

1.70

6,779,100


Palau: ?

2.20

2.20

18,233


Philippines

2.60

2.60

112,508,994


San Marino



34,085


Senegal

4.60

4.60

17,653,671


Sierra Leone

4.30

4.30

8,306,436


Suriname

2.40

2.40

596,831


Tonga

3.60

3.60

107,749


West Bank & Gaza Strip



626,161

2

Afghanistan

4.50

4.50

40,754,388


Antigua & Barbuda

2.00

2.00

99,509


Bahrain

2.00

2.00

1,783,983


Bangladesh

2.00

2.00

167,885,689


Bhutan: R, I, +

2.00

2.00

787,941


Brazil: R, +

1.70

1.70

215,353,593


Brunei Darussalam

1.80

1.80

445,431


Chile: R, F

1.60

1.60

19,250,195


Côte d’Ivoire: R

4.60

4.60

27,742,298


Dominica

1.90

1.90

72,344


Gabon: R, I, F, +

4.00

4.00

2,331,533


Gambia: F

5.20

5.20

2,558,482


Guatemala

2.90

2.90

18,584,039


Indonesia: R, F, SA

2.30

2.30

279,134,505


Iran: F

2.10

2.10

86,022,837


Kiribati

3.60

3.60

123,419


Lebanon

2.10

2.10

6,684,849


Libya

2.20

2.20

7,040,745


Malawi

4.20

4.20

20,180,839


Mali: R, I

5.90

5.90

21,473,764


Marshall Islands: ?

4.00

4.00

60,057


Mexico: R, F,

2.10

2.10

131,562,772


Micronesia: ?,

3.10

3.10

117,489


Myanmar

2.20

2.20

55,227,143


Nigeria

5.40

5.40

216,746,934


Oman

2.90

2.90

5,323,993


PA



0


Panama: R, F, PA

2.50

2.50

4,446,964


Papua New Guinea

3.60

3.60

9,292,169


Paraguay

2.40

2.40

7,305,843


Solomon Islands

4.40

4.40

721,159


Somalia



16,841,795


South Sudan

4.70

4.70

11,618,511


Sri Lanka

2.20

2.20

21,575,842


Sudan: R

4.40

4.40

45,992,020


Syria: SA, PA

2.80

2.80

19,364,809


Tanzania

4.90

4.90

63,298,550


Timor-Leste: PA

4.00

4.00

1,369,429


Tuvalu



12,066


Uganda

5.00

5.00

48,432,863


United Arab Emirates (UAE): F, SA,

1.40

1.40

10,081,785


Venezuela

2.30

2.30

29,266,991


Yemen: SA

3.80

3.80

31,154,867

3

Algeria

3.00

3.00

45,350,148


Angola: R, I, F, PA

5.50

5.50

35,027,343


Bahamas

1.80

1.80

400,516


Benin: R, I, F

4.80

4.80

12,784,726


Bolivia: R, I

2.70

2.70

11,992,656


Botswana: R, I, F

2.90

2.90

2,441,162


Burkina Faso: R, I, F

5.20

5.20

22,102,838


Burundi

5.40

5.40

12,624,840


Cameroon: R

4.60

4.60

27,911,548


Central African Rep.: R, I, F, +

4.70

4.70

5,016,678


Chad: R, I, F

5.70

5.70

17,413,580


Colombia: R, I, F

1.80

1.80

51,512,762


Comoros

4.20

4.20

907,419


Costa Rica

1.80

1.80

5,182,354


Dem. Rep. of Congo: R, I, F

5.90

5.90

95,240,792


Djibouti

2.70

2.70

1,016,097


Ecuador: +

2.40

2.40

18,113,361


Equatorial Guinea: SA, PA

4.50

4.50

1,496,662


Eritrea: R, I, +

4.10

4.10

3,662,244


Eswatini (formerly Swaziland):

3.00

3.00

1,184,817


Ghana: R, I, F, +

3.90

3.90

32,395,450


Grenada

2.10

2.10

113,475


Guinea: R, I, F

4.70

4.70

13,865,691


Israel: R, I, F, +

3.10

3.10

8,922,892


Jordan

2.80

2.80

10,300,869


Kenya

3.50

3.50

56,215,221


Kuwait: F, SA, PA

2.10

2.10

4,380,326


Lesotho: R, I, F

3.10

3.10

2,175,699


Liberia: R, I, F

4.30

4.30

5,305,117


Liechtenstein: R, PA, +

1.60

1.60

38,387


Malaysia

2.00

2.00

33,181,072


Mauritius: R, I, F, PA

1.40

1.40

1,274,727


Monaco: R, I, F, 



39,783


Morocco: SA

2.40

2.40

37,772,756


Namibia: R, I, F

3.40

3.40

2,633,874


Nauru: R, I, F, +



10,903


Niger: F

6.90

6.90

26,083,660


Pakistan

3.50

3.50

229,488,994


Peru

2.30

2.30

33,684,208


Poland: R, I, PA

1.50

1.50

37,739,785


Qatar: F

1.90

1.90

2,979,915


R, I, F



0


Rep. of Korea: R, I, SA, +

1.00

1.00

51,329,899


Saint Kitts & Nevis: †

2.10

2.10

53,871


Saint Lucia: R, I

1.40

1.40

185,113


Samoa

3.90

3.90

202,239


Saudi Arabia: SA, PA

2.30

2.30

35,844,909


Seychelles: R, I, F, +

2.40

2.40

99,426


Togo: R, I, F

4.30

4.30

8,680,837


Trinidad & Tobago: †

1.70

1.70

1,406,585


Vanuatu

3.80

3.80

321,832


Zimbabwe: R, I, F,

3.60

3.60

15,331,428

4

Barbados: R, I, F, PA

1.60

1.60

288,023


Belize: F

2.30

2.30

412,190


Ethiopia: R, I, F, +

4.20

4.20

120,812,698


Fiji: R, I, F, PA

2.80

2.80

909,466


Finland: R, F, +

1.40

1.40

5,554,960


Great Britain: F

1.70

1.70

68,497,907


Hong Kong: R, I, F

1.10

1.10

7,604,299


India: R, F, PA

2.20

2.20

1,406,631,776


Japan: R, SA

1.40

1.40

125,584,838


Rwanda: R, I, F, +

4.00

4.00

13,600,464


Saint Vincent & Grenadines: R, I, F

1.90

1.90

39,730


Taiwan: R, I, F, SA, PA



23,888,595


Zambia: F

4.60

4.60

19,470,234

5

Albania: PA

1.60

1.60

2,866,374


Argentina W14

2.30

2.30

46,010,234


Armenia: PA

1.80

1.80

2,971,966


Australia: 

1.70

1.70

26,068,792


Austria D90

1.50

1.50

9,066,710


Azerbaijan

1.70

1.70

10,300,205


Belarus

1.40

1.40

9,432,800


Belgium W14

1.60

1.60

11,668,278


Bosnia-Herzegovina: PA

1.30

1.30

3,249,317


Bulgaria

1.60

1.60

6,844,597


Cambodia W14 : PA

2.50

2.50

17,168,639


Canada°

1.50

1.50

38,388,419


Cape Verde



567,678


China°: SX

1.70

1.70

1,448,471,400


CroatiaW10 : PA

1.50

1.50

4,059,286


Cuba: PA

1.60

1.60

11,305,652


Cyprus

1.30

1.30

1,223,387


Czech Rep.: PA

1.70

1.70

10,736,784


Dem. People’s Rep. of Korea°

1.90

1.90

25,990,679


Denmark: PA

1.70

1.70

5,834,950


Estonia

1.70

1.70

1,321,910


FranceW14

1.90

1.90

65,584,518


French Guiana



314,169


Georgia: PA

2.10

2.10

3,968,738


Germany

1.60

1.60

83,883,596


Greece: PA

1.40

1.40

10,316,637


Guinea-Bissauº

4.50

4.50

2,063,367


GuyanaW8

2.50

2.50

794,045


Hungary

1.60

1.60

9,606,259


Iceland W22

1.70

1.70

345,393


Ireland

1.80

1.80

5,020,199


ItalyD90

1.30

1.30

60,262,770


Kazakhstan

2.80

2.80

19,205,043


Kosovo W10 : PA, SX



0


Kyrgyzstan

3.30

3.30

6,728,271


Latvia: PA

1.60

1.60

1,848,837


Lithuania: PA

1.60

1.60

2,661,708


Luxembourg W14

1.40

1.40

642,371


Macedonia (formerly

1.50

1.50

2,081,304


Macedonia): PA



0


MaldivesD120

1.90

1.90

540,985


Moldova: PA

1.30

1.30

4,013,171


Mongolia D90

2.90

2.90

3,378,078


Montenegro: PA, SX

1.70

1.70

627,950


Mozambique

4.90

4.90

33,089,461


Nepal: SX

1.90

1.90

30,225,582


Netherlands∞

1.60

1.60

17,211,447


New Caledonia



290,915


New ZealandW20

2.00

2.00

4,898,203


Northern Ireland



0


Norway: PA

1.60

1.60

5,511,370


Portugal

1.40

1.40

10,140,570


Puerto Rico∞



2,829,812


Republic of North



0


RomaniaW14

1.80

1.80

19,031,335


Russian Fed.

1.60

1.60

145,805,947


Sao Tome & Principe

4.30

4.30

227,679


Serbia: PA

1.50

1.50

8,653,016


SingaporeW24

1.10

1.10

5,943,546


Slovak Rep.: PA

1.50

1.50

5,460,193


Slovenia: PA

1.60

1.60

2,078,034


South Africa

2.40

2.40

60,756,135


SpainW14 : PA

1.30

1.30

46,719,142


SwedenW18

1.80

1.80

10,218,971


Switzerland

1.50

1.50

8,773,637


Tajikistan

3.60

3.60

9,957,464


Thailand

1.50

1.50

70,078,203


TunisiaD90

2.20

2.20

12,046,656


Turkey W10 : SA, PA

2.10

2.10

85,561,976


Turkmenistan

2.80

2.80

6,201,943


Ukraine

1.30

1.30

43,192,122


United States∞: PA, 

1.70

1.70

334,805,269


Uruguay: PA

2.00

2.00

3,496,016


Uzbekistan

2.40

2.40

34,382,084


Vietna

2.00

2.00

98,953,541

Total Result


2.20

2.68

7,944,436,655



Posted by at No comments:
Labels: , , , ,

Sunday, 10 April 2022

The Five Stages of Grief, after one of your books is returned on Amazon

 The Five Stages of Grief, after one of your books is returned on Amazon:

Denial – Amazon must have made a mistake, or someone just accidentally hit the return button. It will be fixed soon.

Anger – The cheapskate bought the book, read it quickly and returned it. I hate cheaters like that.

Bargaining – If I could just talk to that reader and explain things, I am sure he or she would re-purchase the book. Maybe if I do a re-write and re-publish, it will never happen again.

Depression – What did I expect, I am a terrible writer and should just give up.

Acceptance – Big deal. My return rate is low, so it doesn’t mean anything. You can’t please everyone. I’ll bet Shakespeare had some unhappy customers, too.



To be honest, returns don’t bother me – I was just looking for something amusing to blog about, and an excuse to do a meme (the drawing is from the internet, the text is mine). :)

Actually my return rate is low, about 0.5%. And it is true, you can’t please everyone. I’m not sure about the Shakespeare thing, though.

Anyway, here is the book that that was returned, and thus motivated this blog. It’’s return rate is about 1.5%. It even did pretty well as a Freebie, back in those halcyon days of Dec 2015.

 

It's Time for a Road Trip – On the Road with Bronco Billy

It's April, and the sun is beginning to come on noticeably stronger in the more temperate regions. Spring is here now, and that brings on thoughts of ROAD TRIP. Sure, it is still a bit early, but you can still start making plans for your next road trip with help of “On the Road with Bronco Billy”. Sit back and go on a ten day trucking trip in a big rig, through western North America, from Alberta to Texas, and back again. Explore the countryside, learn some trucking lingo, and observe the shifting cultural norms across this great continent. Then, come spring, try it out for yourself.

It’s, 99 cents otherwise, but is free every 3 months or so, if you want to watch for it and save a buck.

Amazon U.S.: http://www.amazon.com/gp/product/B00X2IRHSK

Amazon U.K.: http://www.amazon.co.uk/gp/product/B00X2IRHSK

Amazon Germany: http://www.amazon.de/gp/product/B00X2IRHSK

Amazon Canada: http://www.amazon.ca/gp/product/B00X2IRHSK


Here’s the summary:

=======================================================

What follows is an account of a ten day journey through western North America during a working trip, delivering lumber from Edmonton Alberta to Dallas Texas, and returning with oilfield equipment. The writer had the opportunity to accompany a friend who is a professional truck driver, which he eagerly accepted. He works as a statistician for the University of Alberta, and is therefore is generally confined to desk, chair, and computer. The chance to see the world from the cab of a truck, and be immersed in the truck driving culture was intriguing. In early May 1997 they hit the road.

Some time has passed since this journal was written and many things have changed since the late 1990’s. That renders the journey as not just a geographical one, but also a historical account, which I think only increases its interest.

We were fortunate to have an eventful trip - a mechanical breakdown, a near miss from a tornado, and a large-scale flood were among these events. But even without these turns of fate, the drama of the landscape, the close-up view of the trucking lifestyle, and the opportunity to observe the cultural habits of a wide swath of western North America would have been sufficient to fill up an interesting journal.

The travelogue is about 20,000 words, about 60 to 90 minutes of reading, at typical reading speeds.

=======================================================

Posted by at No comments:
Labels: , , , , , , , , ,

Saturday, 2 April 2022

How About a Week in San Francisco (April 1-4, 2022) Free on Amazon.

 

 

U.S.: https://www.amazon.com/dp/B09675F6MJ

U.K.: https://www.amazon.co.uk/dp/B09675F6MJ

Germany: https://www.amazon.de/dp/B09675F6MJ

Japan: https://www.amazon.ca/dp/B09675F6MJ

Canada: https://www.amazon.ca/dp/B09675F6MJ

Australia: https://www.amazon.com.au/dp/B09675F6MJ

India: https://www.amazon.in/dp/B09675F6MJ

As the Covid-19 lockdown is eased, it is natural to want to travel and explore. San Francisco is a world-famous city, one that everyone should try to see at least once in their lifetime.

San Francisco, in central California, is one of the top tourist destinations in the United States. In addition, it generally rates very highly on lists of top “world-class” cities.

What makes San Francisco so compelling? I would say that it is a combination of a beautiful natural setting, a fascinating history and a remarkable blend of cultures, along with a tolerant and welcoming attitude towards newcomers and new things. Plus, there are a great many sights to see, combining a touristy nature and a local “we live here” authenticity.

The book describes a trip of to the city of about a week, which is time enough to see a lot, but not enough time to see even a small fraction of what the city and environs has to explore. In our case, we did a lot of foot-based sightseeing and bus touring in the city and around the bay, as well as taking a nice bus-based wine tour of some of the Sonoma/Napa valley wineries. It was definitely a week well spent. The book is about 20,000 words, about two hours at typical reading speeds.


 



Posted by at No comments:
Labels: , , , ,

Monday, 28 March 2022

Working in Artificial Intelligence and Machine Learning at Electronic Arts and Bioware Presentation, March 25, 2022 (University of Alberta)

 Working in Artificial Intelligence and Machine Learning at Electronic Arts and Bioware Presentation, March 25, 2022 (University of Alberta)

The actual title of this talk was “Machine Learning at Electronic Arts and Bioware”, but I changed the title of the blog to emphasize the “Working in” component. That’s because it seemed to me that the talk was tailored to an audience (mostly university students and staff) who would be interested in knowing what it was like to work in data science at these companies, what data science techniques were used in their businesses and what qualifications would be expected.

I should note that I am just a statistician/data scientist, well along in my career, so I am not interested in a job in this field, just interested in the subject.  But, for any younger people interested in data science and computer gaming, this sounds like a great line of work.  I should also note that there are positions for non-IT people in these fields - for example, a friend of my son is a writer for Bioware (i.e. game scripts, plots and things of that nature).  She seems to like it.

Introduction

  • As many probably know, Electronic Arts (EA) and Bioware are computer game companies (actually Bioware is now wholly owned by EA).

  • Bioware started off as a local company in Edmonton, Canada, which is also the home of the University of Alberta (the U of A has been prominent in academic computer game research for many decades). There are a lot of cross-linkages among these two entities. Bioware’s most successful game is probably “Mass Effect”.


  • Electronic Arts is based in Florida and has produced a plethora of computer games, and is particularly strong in sports-themed games (NFL football, etc).

  • The talk, done by Bioware’s Alex Lucus and EA’s Bill Gordon, was centered on the use of machine-learning (ML) artificial intelligence (AI) algorithms within their companies, for game development and other purposes.

  • It also outlined the connections and partnerships that each company had with government research agencies (e.g. National Research Council) and various academic institutions.

  • It was stressed that there are many opportunities in the gaming world for computer professionals in all stages of their careers, though this talk was especially targeted at students and early career individuals.

  • Given the nature of the talk, it focused on opportunities for those with data science backgrounds. Nevertheless, they stressed that their are many other openings for computer professionals in their companies.

Machine Learning Strategies at Electronic Arts (Bill Gordon)

  • The speaker has a B.S.E.E. (electrical engineering) background and about 8 years experience with Electronic Arts, based in Orlando Florida.

  • He has been involved in many areas that make use of AI and ML at EA, particularly AI for games development and verification.

  • He started out with game development, but is now with the AI support team, which supports all of the company’s teams.

  • He stressed that AI covers a lot of ground at Electronic Arts, including:

    • Game development (e.g. adversarial AI, where the game “plays itself” to learn new strategies).

    • Defect detection within games (looking for errors or inconsistencies within the game, such as a football player with no helmet).

    • Quality Assurance (it has to be bug-free and responsive).

    • Non-game areas, such as marketing and customer support.

  • Game software has a number of requirements, for which AI and ML can be useful:

    • Strict performance standards (e.g. “real-time” playing and realistic appearances).

    • Stability (no crashing or hanging).

    • Timing and synchronization (needing to work well in stand-alone, internet server environment, and mobile apps.

  • There is a mix of traditional AI and newer machine-learning based methods being used, which complement each other. So, a developer should understand both.

    • Traditional AI is basically coding in rules and logic to a game, rather like a traditional expert systems approach.

    • Machine Learning AI can include such aspects as having a non-human opponent in the game, playing “other” characters within the game, or giving hints or instructions to the human players.

  • Electronic Arts has tended to take a “small steps” approach to introducing ML to its games.

  • The focus has been “micro” rather than “macro”. For example, rather than attempting to revamp the entire football game via AI, the focus could be on using AI to train a particular game player, within the game. For example, AI could be used to train running backs on “finding a hole”. It could be counter-productive to try to do too much all at once.

Machine Learning Algorithms Being Used for Game Development and Testing

  • Before getting into the details of ML usage at EA, the speaker emphasized some general matters about coding and AI:

    • The company wants practical applications for advancing the use of AI for matters such as game playing and testing.

    • This means that developers should have a deep understanding of the algorithms and the code used to implement them.

  • Reinforcement Learning

    • Reinforcement learning is based on an “agent” (i.e. a computer generated game player) playing many iterations of a game or part of a game, to improve its game.

    • Perhaps the classic example of this is AlphaGo, which played itself millions of times, and discovered strategies to exploit for success, which human players had never thought of (and thus beat Lee Sedol, the leading human Go player).

    • The agent has a reward function, which is calculated during each iteration of the game or partial game. The algorithm will have the agent try various strategies, to determine which ones offer the most reward (depends on the exact way that the reward function is operationalized for any given game). Those strategies will then be preferred.

    • An agent may do odd “outlier” things that a regular testing regime might miss. For example, a golfing agent might hit the ball backwards, which is a scenario traditional testing might not anticipate, but real human players sometimes do.


    • So, reinforcement learning can help with both “seeking exploits” for game strategies and testing game stability.

  • Imitation Learning

    • This involves having the algorithm learn techniques that have worked for skilled players in the past, and imitating them.

    • Again, using the AlphaGo example, the computer was fed many games between the best humans, as a basis for learning excellent playing strategies. Those could then be augmented by reinforcement learning.

    • For example, in football, real players generate an enormous amount of data (e.g. wearing RFD tags) that EA sports can feed to an ML algorithm, so that if can learn successful strategies.

    • A computer-generated quarterback can then imitate real human players (e.g. Tom Brady), and learn how a computer spots an open receiver.


    • Imitating the real-life actions and behavior of players can also make the game look more realistic, with smoother flow to motions and more genuine-appearing background play.

    • This ML learning can sometimes outperform traditional physics-based AI simulations. For example, imitations, based on thousands of examples of a throw to a receiver on the sidelines, might yield a more realistic appearing arc to the pass than physics-based calculations. The program might also execute faster, which is important in real-time game simulations.

  • Image Classification/Object Detection

    • This involves some overlap between development and testing.

    • Image-classification and Object Detection ML can be useful in detecting anomalies in the game (e.g. a football player who doesn’t have a helmet on, or perhaps doesn’t even have a head).

    • This is rather like an automated “continuity girl” in movie production (someone whose job it is to ensure consistency between scenes).

    • So, it can be used to validate assets or catch bugs.

  • Natural Language Processing, Numerical Analysis, ML Research in General

    • Most games have audio and conversation, so NLP can be used for such matters as having agents make relevant natural-sounding conversation during the game.

Working at Electronic Arts and Bioware

  • Perhaps one of the main messages of the talk was that you can get a job as a game developer at companies like EA and Bioware.

  • They have needs for both traditional programmers and data science professionals.

  • Main skills needed:

    • Programming (obviously), especially C++.

    • That said, programming languages change constantly, so flexibility is vital. Python is also gaining in popularity. Nobody knows what the future may hold.

    • AI and ML skills and knowledge are also obviously important, but that should be in tandem with excellent coding skills.

    • Gaming is a real-time programming task, so it is important that code runs fast and reliably and is easy to maintain.

    • A developer needs to be a quick learner and to have important character attributes such as integrity, adaptability and the ability to get along in diverse teams.

  • Some areas in Game Development teams:

    • game play

    • graphics

    • online game developments

    • systems/analysis.

  • Other areas of IT and Data Science employment with Gaming Companies:

    • finance and marketing.

    • security.

    • tools.

    • translation.

    • QA.

    • data storage.

    • database development, especially server and “big data”.

Questions (from the audience, which was heavily skewed to university students) and Answers

  • What AI Research is going on at Electronic Arts?

    • There is plenty of research going on (e.g. papers/speakers).

    • Some is of the general open-source variety but some is very EA-specific.

    • So, it is both public and internal.

    • An example: a PhD student did research on facial expressionless and gestures, which the company used to help sync these up, for characters in a dice game).

    • There is also research into animation/rendering and cheater detection.

    • The company has huge quantities of data (video, text, etc.) from its games, there there are many possibilities for research.

  • How about at Bioware?

    • Bioware has many research partnerships with government agencies such as NSERC (Natural Sciences and Engineering Research Council of Canada). Many of the problems and research opportunities that interest Bioware also interest research students and academics. The NSERC CREATE grant has been very useful in this regard.

    • Check with Alex.Lucas@bioware.com if these opportunities interest you.

  • What are some of the AI ML techniques that you use?

    • Bill Gordon was not up-to-date on what was being used for strategy games, though he was aware of some experimentation with reinforcement learning.

    • A lot of sports statistics, and RFD tag data (actual players with radio-frequency-tags embedded in uniforms) are used to generate data for game-related analysis, animation, etc..

  • Are you concerned about DeepFakes? Is this a problem for EA?

    • Yes, there is some concern. For example, users can augment aspects of games (e.g. racing car slogans). This can be done in inappropriate ways, that could include DeepFakes.

    • So, the company has to adapt and find new ways to identify harmful augmentations (e.g. NSFW, biased, defamatory content).

  • What about jobs in gaming?

    • There definitely are jobs with Game companies like EA and Bioware.

    • Not all jobs are directly related to games, though. Gaming companies have other important teams that need data science input (e.g. marketing).

    • You need the desire to solve difficult problems, in all sorts of domains.

    • Software of this type has to be quick performing.

    • It does involve “hard work”.

    • You need to be willing to learn and keep on learning.

Some related blogs of mine:

1) The Movie Colossus, the Book Superintelligence and Artificial Intelligence:

https://dodecahedronbooks.blogspot.com/2018/12/the-movie-colossus-book.html

The movie (about 1970) is about an AI taking control of the world, the book(about 201) is about the prospect of the same. Great movie, way ahead of its time.

2) U of A Lecture – Demystifying Artificial Intelligence- Part 1, History of AI: http://dodecahedronbooks.blogspot.ca/2018/03/u-of-lecture-demystifying-artificial.html

3) U of A Lecture – Demystifying Artificial Intelligence- Part 2, Varieties of AI: http://dodecahedronbooks.blogspot.ca/2018/03/u-of-lecture-demystifying-artificial_3.html

From other talks, also given at the University of Alberta, on the general subject of AI and games.

4) Computer vs Human in Go: http://dodecahedronbooks.blogspot.ca/2016/03/go-match-alphago-versus-lee-sedol.html

 

A  5) A Smart Move – AI and Strategy Games.  https://www.blogger.com/blog/post/edit/8998037621231280699/5460797801205874261

 

Now I will plug a book or two:

If you want to get away from computer games and see the real world, you might want to consider a nice road trip, exploring the contrasts between Canada and the U.S.. If so, then “On the Road with Bronco Billy” is definitely your book. 

 

Sit back and go on a ten day trucking trip in a big rig, through western North America, from Alberta to Texas, and back again. Explore the countryside, learn some trucking lingo, and observe the shifting cultural norms across this great continent.  There's even some hockey playoff talk (Oilers-Denver and Oilers-Dallas), for those nostalgic for Canadian playoff representation.


It’s on Amazon (ebook), for a mere 99 cents (U.S.).


Amazon U.S.: http://www.amazon.com/gp/product/B00X2IRHSK

Amazon U.K.: http://www.amazon.co.uk/gp/product/B00X2IRHSK

Amazon Germany: http://www.amazon.de/gp/product/B00X2IRHSK

Amazon Canada: http://www.amazon.ca/gp/product/B00X2IRHSK


Or, if you want to continue contemplating strategic games, you could try “A Dark Horse”, which concerns the troubling run of good luck that a (fictional) horse player experiences, and his extraordinary opponent.

Also on Amazon (ebook), for 99 cents (U.S.).

 



Amazon U.S.: https://www.amazon.com/dp/B01M9BS3Y5

Amazon U.K.: https://www.amazon.co.uk/dp/B01M9BS3Y5

Amazon Germany: https://www.amazon.de/dp/B01M9BS3Y5

Amazon Canada: https://www.amazon.ca/dp/B01M9BS3Y5



Posted by at No comments:
Labels: , , , , , , , , , ,
Subscribe to: Posts (Atom)