YL
Downloads
lifebeyondzetta.docx
>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

Friday, May 22, 1970

 

Who's redesigning cooperation networks ahead of what Stanford Human AI leaders are descirbing the great innovation inflection point ever seen in recent memory.

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.

profile picture

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.

No comments:

Post a Comment