MONTH OF 3 GREATEST AI SUMMITS EVER

ED: Hello all selection errors mine alone chris.macrae@yahoo.co.uk Wash GC- i have tried to share brillaint and kind brain connecxtions - bon courage as humanity's 5 years to 2030 choose whether we are nature's smartest  race or her next dodo!

From 1951 Von Neumann & The Economist merged their ideas on intelligence interviewing of biggest decision makers.

 Journmalistically Neumann's huge contribution was to time pretty accurately 3 rising intelligence waves : million times more compute eg Moores Law- multiplying million times more death of duistance in satelkllite transmission of data/intekigence bverween evert gps; billion times more mapping of society's and narure's deepesst data gravities. In our 1984 report- we guessed the world's most inetlligennt darata reconcilations would be proposed by a taiwanese entrepreneur and a swedish postmaster. I guess we were three quarter au point. see 2025 report chapter 6

 Jensen Huang Friends of Nvidia's rise since 1993  and partnerships are so far advanced in 20 dimensions of humanity and data analysis that usually one summit (eg Spring GTU near santa ckar hq or summer taiwan computex) is a greatest update but 3 in a month is a fantastic treat - oh lucky DC, Mumbai, Tokyo . Fortunatlely most are onm dmmand. I have been trying to find a way to cahat bout this - partly to celebratte 43rd year of 2025 reporting. I think a relaible approach goes backk to asking whos mapping what sata 

here is a rehearsal with gemini- plese note this is a living document - this versuoion mid october 2024

Yes, Earth-2 is a unique space due to its proximity to deep data partnerships and its focus on understanding our planet and its climate.

Here's why:

1. Deep Data Partnerships: As a project developed by NVIDIA, Earth-2 has access to a vast array of data and computational resources. This includes data from satellites, weather stations, climate models, and other sources, which can be used to create a highly accurate and detailed simulation of Earth.
2. AI and Machine Learning: Earth-2 leverages advanced AI and machine learning techniques to analyze and interpret the massive amounts of data used in the simulation. This allows for complex modeling and prediction capabilities.
3. Climate Focus: Earth-2 is specifically designed to study and understand climate change. This makes it a valuable resource for researchers and policymakers who are working to address the challenges posed by climate change.

In summary, Earth-2's unique combination of deep data partnerships, AI capabilities, and focus on climate science make it a valuable tool for understanding and addressing global environmental challenges.

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

deep data - grounded in reality of community - expert or human (eg family loving women of bangladeshz):

Can you remind me who started the proyein folding data competition whiich Hassabis deep mind eventually won with alphafold?

 This biennial competition was founded in 1994 by John Moult, a computational biologist at the University of Maryland.

Are there other famous data competitions as far as AI is concerned in addition to CASP and Fei0Fei Li's imagenet? If so are any in the top league the way casp and imagenet seem to be?

Yes, there are several other famous data competitions in AI, in addition to CASP and ImageNet. Here are a few of the most notable ones:

Image Classification:

• CIFAR-10 and CIFAR-100: These are smaller datasets compared to ImageNet, but they are widely used for benchmarking image classification algorithms.
• Places365: A dataset of 365 scene categories, used for scene recognition and localization.

Natural Language Processing:

• GLUE (General Language Understanding Evaluation): A benchmark for evaluating the performance of natural language understanding systems on a variety of tasks, such as question answering, text classification, and sentiment analysis.
• SQuAD (Stanford Question Answering Dataset): A dataset for machine reading comprehension, where the goal is to answer questions based on a given passage of text.
• WMT (Workshop on Machine Translation): A workshop that includes a machine translation competition, where participants compete to build the best machine translation systems.

Speech Recognition:

• LibriSpeech: A large-scale speech recognition dataset, used for training and evaluating automatic speech recognition systems.
• TIMIT (Texas Instruments-MIT Spoken Sentence Corpus): A smaller dataset of phonetically balanced American English sentences, used for speech recognition research.

Other:

• Kaggle Competitions: Kaggle, a platform for data science and machine learning, hosts numerous competitions on a variety of topics, including image classification, natural language processing, and time series analysis.
• Netflix Prize: A famous competition that was held in 2006-2009, where participants competed to improve the accuracy of Netflix's movie recommendation algorithm.

These competitions have played a crucial role in driving progress in AI research and development. They provide a common benchmark for researchers to compare their methods and algorithms, and they often lead to significant breakthroughs in AI.

While CASP and ImageNet are undoubtedly among the most influential data competitions, the others listed above are also highly regarded and have made significant contributions to the field of AI.

Imagenet took a long time to set up (both years elapsed time and if one counts identification of 20 millionn images by amazon tutk) many years of haumn time- did casp take long time to set up?

Yes, CASP (Critical Assessment of Structure Prediction) also took a significant amount of time to set up.

While it doesn't involve the massive scale of image identification like ImageNet, CASP has involved:

• Decades of Protein Structure Research: The foundation for CASP lies in decades of research on protein structure prediction methods.
• Collaborative Efforts: The CASP initiative itself has been a collaborative effort involving researchers from around the world, coordinating experiments and evaluations.
• Data Collection and Preparation: Preparing the protein structures and associated data for CASP experiments requires significant time and computational resources.

While the exact timeline might vary depending on specific CASP iterations, it's safe to say that the setup and execution of CASP experiments have involved a substantial investment of time and effort from the scientific community.

My first of 16 trips to Bangladesh Xmas 2007- this interview was a great gift- it helped friends see the deepest entreprenurial revolutio9n of going mobile; 2 years later in stanford the idea of mobile data clouds encouraged at least 4 people togo all in with AI Revlution namely Jensen Huang - he would build compouters capable of million time more com0puting power; fei-fei li- she would run global cometitions until big data analysis showed machines could selarnb to see and speak about the 2000 objects huamns mos use; demis hassabus would start designing natirual science mpodels to that computational analysis could leap forward to where Einstein's throy got to in 1905! Andrew NG was already the coder people at stanford trusted most and starting up cousrera/moocs

.Note far the most sustaiably inteligence network maps round bottom of pyramid poorest asian vilager women- 1 billon girls who have also pulled up males lives in their communities. This m0ovement waslinked together from the earl;y 1970s : the common needs were end starvation, and in the humid tropics end infant deaths by diarrhea. It shopuldnt be surprising that the solutions needed were boderless across vilage tropics (wherever electricity griuds had not reached). Today the purest models of thios sort connect with Bangla2/0 a governace model Muhammad Yunus has been asked to map since august 2024- the vast majority of nations could gauin from connecting with this model The goal 2 food intelligence of this model starts with Borlaug. From idaho his lab was in mexico and his first target crop for up to 10 times small farmer produvtivity was wheat. If you go to the food prize you will see how what bprlaug started became worldwiode intelligence for every staple crop. For Asia ricer was most important- by late 1960s Japan Korea S Taiwan were procuing 10 times more rice per small farmer than historically had been seen. Mainly US foundatiosn started IRRI out of Phillipines and a twin intel hub out of taiwan. It apears to uis that Taiwan was where most of the billion girl movemnt rooted intel to achieve goall 2 end starvation. Countries were partocularly sucessful wherer microfranchise busienss models however small were designed not chjarity in generating this miraculous advance. We are not very keen on term microfionace. It was primarily sharing inmtel (ie education) that empowered vilage mothers to microifrancise small for profit businesses be they in  meeting last mile food needs or inmcirculating the most basic health solutions. Up until 1990s viulafers communicated by word of mouth or print of book having no electricity andf no communications machines. From late 1990s partners brough both mobile and solar (charging mobiles) so unique l;eapfrog models could be stidudied in communities that never had aces to grids (electricity, telecopm or other). Again Bangladesh led by 2 wizards Fazle Abed and Muhammad Yunus became a place to benchmark. This is also why anyone serously involved with UN goals would in fall 2024 track ways of helping Bangladesh map gov2.0 . This had been an exercise that THE UN had launched as UN2.0 in 2016 but where erors have been made so that articfiacial intel and un2.0 are not yet synchroniised. Again this is a a reason why the low tech next goverance model of Bangladesh is relevant as of course are hi-tech deep lerning models of wizards such as Jense Huang

2025reoort.com join our 75th year of debating with ada whether the inteligence machines of the NET Neumann Einstein Turing would advance or destroy humanity. Von Neumann set the 75 year timeline- he ssxaw these machines as connecting every human being's potential with nature and each other. Indeed since Einstein's publication in 1905, maths shows taht newton's science was wrong when humans start scaling stuff at nature's scale. Her system designs map bottom up and without the sorts of bodrers the era of Empires found it conveneint to administer. In other words, to the NET many of humanity's biggest rishks would cokpound at borders be these geographical or where one [profession ends its responmsibility assumingt another will take over, Banking  insurance law and other professions when adminsitered in silos cannot compound solutions to what are the goals we would wish to support at least any child (it being unclear at what age individual responsibility takes over from society), But most places systems imply this is somewehere between 13 and 18.  We can list some people alive and dead which we feel intelligence is beter if you are aware of their dicoveries. We can map some places eg Singapore and Taiwan where people sem to have advabnced by win-winning with rest of the world. Although the UN sdgs are not our favorite we will classify some intyel solutions by goals. The EN currently clarifies most goals are collap[sing. Perhaps V Neumann will alow us 3 y intelligence isnt aligned to sdgs out of more and more com,mmunities then it is mathematically unlikely our spocies wil see a 22nd century. We welcome serious correpondence . One problem is we have not folowed v neumans advice. Expect 3 tranbfromational waves: computation eg moores law brough million times more computation capactiy 1965-1995 Data or inte transmission between everywjere on earth - eg satllite telceoms mobilsed such data cloiuds sooon after 2010 Analysis as earth's depth needs compiuters designed to analyse interactions at earths scale. Weather is juist one exzmple. Thanks to this who folowe Jensen Huanmg since 1993 such deep learning computers exist. See 8000 partial inventions partners of huang talk about as well as his annual reviews since 2015.