economistsocial.com publishers world record book of jobs creation (worldrecordjobs.com): berkeley stanford and deep mind

>3/18 24: Similarities between Electronic Computers and the Human Brain: Thank you Jensen Huang for best week of Learning since John Von Neumann shared with The Economist 1956 notes Computer & The Brain

HAPPY 2024: in this 74th year since The Economist started mediating futures of brainworking machines clued by the 3 maths greats NET (Neumann, Einstein, Turing) people seem to be chatting about 5 wholly different sorts of AI. 1BAD: The worst tech system designers don't deserve inclusion in human intel at all, and as Hoover's Condoleezza Rice . 2 reports their work is result of 10 compound techs of which Ai is but one. Those worst for world system designs may use media to lie or multiply hate or hack, and to perpetuate tribal wars and increase trade in arms. Sadly bad versions of tv media began in USA early 1960s when it turned out what had been the nation's first major export crop, tobacco, was a killer. Please note for a long time farmers did not know bac was bad: western HIStory is full of ignorances which lawyer-dominated societies then cover up once inconvenient system truths are seen. A second AI ecommerce type (now 25 years exponential development strong) ; this involves ever more powerful algorithms applied to a company's data platform that can be app'd to hollow out community making relatively few people richer and richer, or the reverse. You can test a nation's use of this ai by seeing if efinance has invested in the poorest or historically most disconnected - see eg bangladesh's bklash, one of the most populous digital cash systems . Digital money is far cheaper to distribute let alone to manually account for so power AI offers lots of lessons but whether its good or not depends in part on whether there are enough engineers in gov & public service to see ahead of what needs regulating. There are 2 very good ai's which have only scaled in recent years that certainly dont need regulating by non engineers and one curious ai which was presented to congress in 2018 but which was left to multiply at least 100 variants today the so-called chats or LLMs. Lets look at the 2 very good ai's first because frankly if your community is concerned about any extinction risks these AI may most likely save you, One I call science AI and frankly in the west one team is so far ahead that we should count ourselves lucky that its originator Hassabis has mixed wealth and societal growth. His deep mind merged with google to make wealth but open sourced the 200 million protein databank equivalent to a billion hours of doctorate time- so now's the time for biotech to save humanity if it ever does. Alongside this the second very good AI graviates around Fei-Fei Li) in developing 20 million imagenet database so that annual competitions training computers to see 20000 of the most everyday sights we humans view around the world including things and life-forms such as nature's plants and animals. Today, students no longer need to go back to 0.1 programming to ask computer about any of these objects; nor do robots or and autonomous vehicles - see fei-fei li's book worlds i see which is published in melinda gates Entrepreneurial Revolution of girl empowerment

EW::ED , VN Hypothesis: in 21st C brainworking worlds how people's times & data are spent is foundational to place's community health, energy and so natural capacity to grow/destroy wealth -thus species will depend on whether 1000 mother tongue language model mediates intelligence/maths so all communities cooperatively celebrate lifetimes and diversity's deep data ) . Check out "Moore exponential patterns" at year 73 of celebrating Game : Architect Intelligence (Ai) - players welcome .. some jargon

Monday, September 25, 2023

berkeley stanford and deep mind

Nobel Laureate and gene databank CRISP founder Jennifer Doudna is at Berkeley

is there an ai person at berkeley who may connect doudna and eg alphafold2 progress in practical areas of protein breakthrough

Bard replies

Yes, there are several AI researchers at UC Berkeley who could potentially collaborate with Jennifer Doudna on applying AlphaFold2's protein structure prediction capabilities to practical areas of protein engineering. Here are a few examples:

Pieter Abbeel: Abbeel's expertise in reinforcement learning could be used to develop algorithms for optimizing protein design and engineering.
Anca Dragan: Dragan's expertise in robot learning could be used to develop robotic systems that can perform protein manipulation and synthesis.
Michael Jordan: Jordan's expertise in machine learning and Bayesian statistics could be used to develop algorithms for predicting protein interactions and function.
Sergey Levine: Levine's expertise in reinforcement learning and control theory could be used to develop algorithms for controlling protein folding and assembly.
Stuart Russell: Russell's expertise in artificial intelligence, machine learning, and robotics could be used to develop AI-powered systems for protein design and engineering.

In addition to these specific researchers, there is a large and active AI community at UC Berkeley that could provide valuable expertise and collaboration opportunities for Jennifer Doudna's work on protein engineering. The university's strong research infrastructure and resources would also be a valuable asset for such collaborations.

Here is a specific example of how AI could be used to apply AlphaFold2's protein structure prediction capabilities to practical areas of protein breakthrough:

Protein design: AI could be used to design new proteins with desired properties, such as increased stability, catalytic activity, or binding affinity. This could lead to the development of new drugs, enzymes, and materials.
Protein engineering: AI could be used to engineer existing proteins to improve their function or to add new functionalities. This could lead to the development of new therapies for diseases or the creation of new industrial enzymes.
Protein structure prediction: AI could be used to improve the accuracy of protein structure prediction methods, such as AlphaFold2. This could lead to a deeper understanding of protein function and the development of new drugs and therapies.

The potential applications of AI in protein engineering are vast and are only beginning to be explored. Collaborations between AI researchers and scientists like Jennifer Doudna could lead to significant breakthroughs in this field.

================ Is Ian Stoica - speaker at Radical Ventures Toronto masterclass a top ai person at berkley- who else is ? (Now that Hinton is no longer at To9rnto full time Radical Vnetures is ome of ai event webs to track)

Bard answers

Yes, Ian Stoica is a highly respected AI researcher and professor at UC Berkeley. He is known for his work on machine learning, natural language processing, and reinforcement learning. He is also a co-founder of the Berkeley Artificial Intelligence Research (BAIR) lab, which is one of the leading AI research labs in the world.

Here are some of the other top human AI professors at UC Berkeley:

Pieter Abbeel: Abbeel is a professor of computer science and robotics at UC Berkeley. He is known for his work on reinforcement learning and robotics. He is also a co-founder of covariant.ai, a startup that is developing self-driving cars.
Anca Dragan: Dragan is a professor of electrical engineering and computer sciences at UC Berkeley. She is known for her work on robot learning and human-robot interaction. She is also the director of the Berkeley Robot Learning Lab.
Michael Jordan: Jordan is a professor of computer science and statistics at UC Berkeley. He is known for his work on machine learning, Bayesian statistics, and artificial intelligence. He is also a co-founder of the Data Science Institute at UC Berkeley.
Sergey Levine: Levine is a professor of electrical engineering and computer sciences at UC Berkeley. He is known for his work on reinforcement learning, robotics, and control theory. He is also the director of the AUTOLab at UC Berkeley.
Stuart Russell: Russell is a professor of computer science at UC Berkeley. He is known for his work on artificial intelligence, machine learning, and robotics. He is also the co-author of the textbook Artificial Intelligence: A Modern Approach, which is one of the most widely used AI textbooks in the world.

These are just a few of the many outstanding AI professors at UC Berkeley. The university is a leader in AI research and education, and its faculty members are making significant contributions to the field.

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

Nov 2023 bill gates says all change education with AI but are ed systems/peoples ready?

Update Thanksgiving 2023
83.0 EconomistLearning logs experiences including future-back imagineering we have seen 40 years of cooperation with real teachers starting in new zealand; these clusters were concerned transforming livelihoods 10 years ahead as any school system responsible for eg 10 years of a childs development needs to be
83.1 as of 2023, regarding school life: we dont know AI that is better than a good teacher or time-rich parent of kids up to 16
83.1b equally there are now many subjects from age 5 up - eg dance physical exercise drawing where an AI can help any teacher improve her class performance

83.2 ironically when it comes to professors/colleges we dont know any professor worth studying with unless she or he connects with best relevant ai - currently this means partnerships generally with a very few places though specifically wherever is best at ai
83.2b there is also confusion - these days if you have access to superchats/llms increasingly most people dont need to be great mathematicians or even great coders to be very competent at making use of ai that their expertise/jobs needs most;
83.2c however what always be a valuable design skill is a kind of pattern analysis that is often somewhere half between maths and architecturally seeing/blueprinting a discipline

83.3a of course there are nuances to this and the problem of what sort of digital access is needed in different nations or regions; much ai can now be used the same way you use a mobile app but not necessarily created that way
83.3b there is also a problem that powerful old people may not want to hear that they are now putting a lot at risk of they dont help everyone see worlds ai can see; please note when we use word ai we mean all technologies -please see condoleezza (hoover at stanford) report on top 10 techs multiply ai and each others usability; and eg ask her teams if you need more specific context risk/foundations checking
83.3c one of the big things: all over the world the most work that needs to be done is locally, communally- ai can be very good at helping teams build emotional intelligence as they daily serve communities ; paradoxically old schools spent very little time on team as opposed to individual attainment; in this regard every teacher needs to demand change in school processes; fortunately ai can be very good at helping with that attending to sort of administration transformation

chris.macrae@yahoo.co.uk I am happy to offer a free 30 minute zoom or whatsapp -who wants to discuss the above openly; I realise in some regards I am over-simplifying and enjoy learning what is stopping people from uniting around very good ai- see my views on where education could be written 40 years ago after my first 10 years studying computers in education and regarding societal needs across many countries with database tech supplied my MIT/harvard; in these 2020s, its not the tech or the youth that is stopping personalised learning it is in some sense that elders have not attended to the personalised learning agency everyone could now have - see eg recent changes of views on this eg bill gates

AIC1... & Who's redesigning cooperation networks ahead of what Stanford Human AI leaders are describing the greatest innovation inflection point ever seen in recent memory see Google ceo pichai announced these as major accomplishments of google brain and deep mind when he asked them to merge lastApril 2023. Their collective accomplishments in AI over the last decade span AlphaGo, Transformers, word2vec, WaveNet, AlphaFold, sequence to sequence models, distillation, deep reinforcement learning, and distributed systems and software frameworks like TensorFlow and JAX for expressing, training and deploying large scale ML models Please can you give me for each of these innovation areas some references including an overall description of each that a 5th grade teacher could adopt to make sure that teens are monitoring these opportunities in making 2020s more and more human

Sure, here is a brief overview of each of the innovation areas that you mentioned, along with some references that you can use to learn more. I have also included some ideas for how a 5th grade teacher could adopt these technologies to help their students learn and grow.

AlphaGo

AlphaGo is a computer program that was developed by Google DeepMind to play the game of Go. In 2016, AlphaGo defeated a professional Go player, Lee Sedol, in a series of matches. This was a major breakthrough for AI, as Go is a very complex game that was previously thought to be too difficult for computers to master.

Transformers

Transformers are a type of neural network that are used for natural language processing tasks. They are particularly good at tasks such as machine translation, text summarization, and question answering.

Word2vec

Word2vec is a method for learning the vector representations of words. These vector representations can be used for a variety of tasks, such as text classification, sentiment analysis, and natural language generation.

WaveNet

WaveNet is a neural network that can be used to generate realistic speech. It is used in Google Assistant and other voice-activated products.

AlphaFold

AlphaFold is a protein folding prediction program that was developed by Google DeepMind. It is able to predict the structure of proteins with unprecedented accuracy. This could have a major impact on the fields of medicine and biology, as it could help scientists to better understand how proteins work and how they can be used to treat diseases.

Sequence to sequence models

Sequence to sequence models are a type of neural network that can be used to translate text from one language to another. They are also used for tasks such as machine translation, text summarization, and question answering.

Distillation

Distillation is a technique that can be used to improve the performance of a machine learning model. It works by transferring the knowledge from a large, complex model to a smaller, simpler model.

Deep reinforcement learning

Deep reinforcement learning is a type of machine learning that can be used to train agents to learn how to behave in complex environments. It is used in a variety of applications, such as robotics, game playing, and finance.

Distributed systems and software frameworks

Distributed systems and software frameworks are used to develop and deploy large-scale machine learning models. They provide a way to manage the resources required to train and run these models, and they make it easier to develop and deploy models across multiple machines.

How to use these technologies in the classroom

There are many ways that teachers can use these technologies in the classroom. For example, they can use AlphaGo to teach students about the game of Go, or they can use Transformers to help students learn about natural language processing. They can also use Word2vec to help students learn about the vector representations of words, or they can use WaveNet to help students learn about how to generate realistic speech.

In addition to these specific technologies, there are many other ways that teachers can use AI in the classroom. For example, they can use AI to personalize instruction, to provide feedback, or to grade assignments. They can also use AI to create interactive learning experiences, or to help students learn about complex topics.

The possibilities are endless, and it is up to each teacher to decide how they want to use AI in their classroom. However, one thing is for sure: AI has the potential to revolutionize education, and it is something that all teachers should be aware of.

View other drafts

Sure, here are some of the practitioners who could benefit from following the latest AI models from Google DeepMind:

Biotechnologists

As you mentioned, AlphaFold has the potential to revolutionize biotechnology. It could help scientists to better understand how proteins work and how they can be used to treat diseases.

Pharmacologists

Pharmacologists could use AI to design new drugs and to better understand how existing drugs work.

Chemical engineers

Chemical engineers could use AI to design new materials and to improve the efficiency of chemical processes.

Materials scientists

Materials scientists could use AI to design new materials with specific properties, such as strength, lightness, or conductivity.

Engineers

Engineers could use AI to design new machines and to improve the efficiency of existing machines.

Scientists

Scientists in a variety of fields could use AI to help them to collect and analyze data, to make predictions, and to develop new theories.

Businesses

Businesses could use AI to improve their operations, to make better decisions, and to develop new products and services.

Governments

Governments could use AI to improve their services, to make better decisions, and to protect their citizens.

These are just a few of the many practitioners who could benefit from following the latest AI models from Google DeepMind. AI is a rapidly developing field, and it is important for practitioners in all fields to stay up-to-date on the latest developments.

what was known about EDforgood 1999 -web1 decade

while web2 was to change everything again - did enough people understand these lessons in plain sight from 1990s decade of web1? see page 41/42 from decade report by Gordon Dryden out of new zealand celebrated by 10 million Asian families

The 13 steps needed for a 21st century education system Imagine a 21st century community where:
Every student has his or her own laptop computer.
Every home has its own combined computer - television set at a cost of only $300, or possibly much less.
Every home and every student is connected to the Internet.
Every person, at almost any age, can have instant access to the world's best teachers in any subject.
Each can also select at random from the world's best libraries, interactive science museums and art galleries.
Each is linking up regularly with others around the world, designing their own electronic games to teach their own favorite subjects.
Every new parent is trained to be able to develop each child's fantastic early potential, to be able to identify different temperaments, and different learning and thinking styles.
Every four-year-old can read, write, spell, count, add, subtract, multiply, divide, compose her own stories, draw, paint - and speak three or four languages - but they've learned all this with fun and games.
The health of every child from birth is regularly monitored to ensure his eyesight, hearing and other senses are in great "learning order".
Every five- or six-year-old starts school with an equal opportunity to develop to its full potential.
School itself is the best party in town: a base from which to explore the whole wide world of experience and knowledge.
ABOVE WAS VERY EASY FOR RICH NATIONS TO DESIGN. TRAGICALLY BY FAILING TO DO SO POOREST PLACES SUSTAINABILITY GOALS WOULD GET EVER LESS POSSIBLE UNLESS UN2.0 becomes benchmark for gov2.0 anywhere children/next generation needs to develop

Intel Toolkit est 1951 - 3 keys mediating economics & AI to 2025- Source Economist & von Neumann

Mapping good ai for 2025 from 1951 Neumann/Macrae

100 times more tech connecting"good" if it

unites worldwide advances in (what we now call ) UN SDGs1 to 6

Starting with poorest – ie basics of life

2 Food , 6 water,3 health, 4 livelihood ed3, 5 no

Underclasses, safe home

In addition birth of UN in 1945 recognized that up to 75% of

Peoples had been left out of electricity grids

Etc by way Empi9re world was designed-with

Particular crises of landlocked nations or peoples

Far from coastlines- this would need urgent

Cooperative attention in era of independence

As of 1045 only nations controlled by Stalin

appeared not to agree with UN goals;

World would need to outlast Stalin and

Avoid nuclear bombs until old world’s far north

People free ; thence hopefully disarmament

In picture name 3 as "math wizards deep data science"-\

if ai and economics design what human relationship futures are possible, then bothwWill need maths wizards as grounded as eg those of TEN – Turing Einstein Neumann

V Neumann's life had been dominated to 1945

By crises and gov secrets of energy projects, he wanted to dedicate

Rest of his time to intel of hardware

Coding and brain science; as of 1951 he didn’t

know he had less than 6 years; Einstein and

Turing less than 3; he did know he wanted to

Open source everything on AI

RESOURCES Regarding future exponentials of tech and humans and UN

ITU publications since 1865; League of nations diaries including Einstein

Hosting of international intellectual cooperation; Geneva as Digital, trade mapping and health twin

of UN from 1945

Major sources: diaries and letters of TEN eg note Einstein letters to Gandhi & Freud; Diaspora Scots school including Adam Smith and from 1843 Economist James Wilson And Royal Family diaries UK Netherlands; Bagehot English Constitution;

Keynes especially last chapter general theory; Geoffrey Crowther publication

Economist Autobiography 1843-1943

......................................

timing.the age of humans and machines dd not begin to 1760s scotland- until then most people did not move more than 15 miles from place of birth unless they lived near water; there was one exception that had emegerged in the old world ; it was an overland market relay connecting the 2 greates bay areas of the old old world-to the west the med sea the bay that connected asia to the 2 other known continents europe to the north and africa to the south
the great bay area that mainly tranversed from the islabnd of japan to the coastlines of korea and china as far as the place we now call shanghai and down the river to hangzhou- marco polo had called hangzhou the town with the greatest range of marketing goods he had ever seen; it was at the intersection of 3 trading routes; an inland canal up to beijing; where the overland silk road ended an transferred produce to boats which then salid up the river to the great bay..

first 7 year report on brac posted 1979: village women are learning to read & write: they are finding out about the causes of poverty and disease around them
they are teaching one another about farming and weaving, health and medicines; they are assuming public roles of leadership and management
for the first time in their history; they are contributing to local economic development through successful production cooperatives; it is hard in the West to imagine the drama involved in such profound changes

world war 2 and was now looking to design wi-in trades with asians; over the next 15 years my father clarified the 2 asian capitalism models as rural keynesianism which abed/bandgladesh women beccame purest benchmar of; coastal belt caqpitalism which jpapan the korea the diaspora chinese in taiwan hk singapore led until china asked japan to share its borlaug/quality engineerind knowhow in late 1970s; it was after 1976 that china transformed businesses from just state owned ones include secondly village owned ones; 3rd billion dollar inward investments from the diaspora mainly in supercoty infrastructure incluing world class ports and trains

related collaborations economistdiary.com abedun.com girlsworldbank part 2 ecop26.com
50 YEAR SEARCH FOR HumansAI top 100 hUNIcorns (networks that never exit life-dev purpose) - from 100000 village to first 50 new universities who share sdg alumni- also current top 10 at worldrecordjobs.com abed 2 3 4 5 6 7 8 9 10

.Economistmaps.com Goodhubsguide.com dedicates freedom & happiness of rural keynesianism TO fazleabed.com & chinese barefoot medics since 1970, all women under 30- quarter of humans- 90% of sustainability solutions......................

WHICH ORBITAL GOALS INTEGRATE YOUR HUMAN DEV NETWORK ?
0 hi-TRUST COMMUNITY DATA O/S OR
1 POVERTY
2 STARVATION
3 HEALTH
4 EDU

hU01 when fazle abed first built 16000 homes for
100,000 villagers he did not realise that over the
next 50 years this would become the deep data lab for
microfranchise solution partnering in helping empower
village women build the rural nation of bangladesh and
that chinese village women needing similar solutions
would incorporate social business capitalism into china's
rural keynesianism- all told 1 billion asians would not
have improved health, ended famine, become the world's -celebrated greatest education leaps with the least resources without resilient
& safe community building -more on hu01

Are you influencing your city's green collaboratory events? - example among 40 in-network collaboration cafe cities new yorkers helped mediate this 2009 while americans were free to celebrate green millennials

.BBCGREEN & Bangla5000 selections 2021-2000
21 lbs- africa's turn +hunicorn100 hughes
21-health equity:LBS: -cf astra.place AI 18..19..20..21
19 50 years building number 1 ngo collab with abed bhai.. GATES __NotesU-saving lives
13 khan asks musk- did your college plan include taking over NASA
03 bezos - gold rush or next electricity

over 50 million Chinese died of famine by mid 1960s so by 1968 chinese village parents began Goals1-4 search; bangladesh joined in by 1972- its bangladesh story we have spent 10 years researching ... already by 1960s japanese koreans and chinese diaspora had the money and the motivation to help all asia rise...

Friday, April 16, 2021

For some engineers, building 16000 homes at 5 dollars each housing total of 100000 people might have been miracle enough but then abed saw 16000 village mothers and 60000 kids starving or dying of diseases like diarrhea- so he designed microfranchise businesses for women to be the village food security and basic health servants - and two american chinese missioaries said can we swap some of your village micrfranchises (we need oral rehydration) with those in village china;

and then james grant of unicef said why not replicate your village solutions all across bangladesh, and is there something extra unicef can do for you - abed said can you arrange for the government to vaccinate half of bangadesh while our village networks do the other half. and so a blend of bottom up disater relief and sustainable micrfranchises became the world's largest ngo partnership- and all the while bottom up hunicorns networks had no taxes or traditional top down aid- empowerment is a very different way of nation building- and across the two thirds of humans who are asians - women just did it whereve extreme poverty was ended

hu01 - resilient community hu02 oral rehydration -nation wide moters training

huo3 -last mile hrlth service franchise - one village women weekly door t door 300 homes selling basic non-prescrition drugs and being mothers source of health news

hu04 - 5 times more productive village rice production...

zzz

mapping 6 ways youth

and families can exponentially sustain increasing productivity by making every community a thriving place to grow up in
systems crisis: while each of the 6 ways offers growth beyond the reality let alone imagination of what is possible without access to the new way, if we exclude some peoples lives from access to the new way then we will lose sustainability of our species- example by 1939 we'd reached world war 2; the root cause was slavery, treating huge populations of people as underclasses with no access to electricity grids or other win-win uses of ir1 and ir2; it took us 180 years for first machines glasgow 1760s to get into this worldwide collapse; the mathematician von neumann worked feverishly for 12 years to deliver ways out of this mees ir3, ir4; within 2 years of his death in 1957, jfk had declared moon landing was possible; ai labs stuying the ultimate consequences of ir3,ir4 had been twinned out of staford facing asia pacific, out of mit boston facing the old world- the 7 white of the big g8 empires whose 12% of people had colonised most of plant earth as if the majority of peoples lives did not matter including the two thirds who are asian and in america those whose skin colors had beem slaves; within 4 years of stanfords ai lab intel had such a huge order from a japan calculator manufacturer replacing slide rulers that the programable chip was invented so as not to be beholden to one client; and gordon moore declared his aluni would multiply 100 times more comp and coms (ir2.1) power every decade to 2020s when chips would rival switching powers of human brains- and computers could run real time platforms previously requiring manual government . So getting ir3, ir4 exponentially right -for every next child born -notably goals 1-6 as basics for life and natural diversity let alone futureoflife- had 75 years to tik tok from birth of the united nations.
0 agriculture
*ir1 = energy machines -engines delivering thousands then millions time more horsepower and infrastructure both transportation and pipelines -eg electricity, fuel, water enabled big cities to emerge as most peoples
*ir2 telecommunicating machines eg telegraph telephone radio television satellite mobile
* ir3 computing tools for human productivity beyond slide rules and paper reporting
*ir4 AI= Artificial Intelwhen computers taking over governing real time platforms
*society 5.0 gravitating livesmatter where every society next child is born in is a great place to grow up because it maximisse peace, culture, natural diversity win-wins including healthy connections with other places

inspired by fazle abed we are searching for HUNIcorns- global village sustainability solution networks too vital to exit

HUNI0 is where sir fazle aded started up global uni of poverty 50 years ago with a field lab of 100000 poorest villagers

HUNI100 - is the legacy - abed brac university which he started branstorming partners around 1999 - to celebrate both a new millennium and his 4th, 5th decades of end poverty networking

we see 5 action compasses of unicorns as gravitationally core to the bottom-up servant leaders maps designed by abed and partners who turned brac into the world's largrst and deepest ngo networl:

last mile health servant unicorns

ending poverty with financial unicorns

ending hunger with food/warter security unicorns

lifelong livelihood education unicorns for all ages

resiliemnt/safe social spaces so next child born anywhere has good chance to thrive