Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Language Models Explained From Zero to Deep. No Magic, Only Mathematics #aitutorial #aiforbeginner #howaiworks #techdeepdive #aiengineering

The Tech Prophet (Amospikins)

25,815 subscribers

189,569 views • 6 months ago •via X (Twitter)

Arts Education Science & Technology #aitutorial #aiforbeginner #howaiworks #techdeepdive #aiengineering

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

India was centuries ahead in mathematics. In the 7th century, Brahmagupta built on Aryabhata’s work and was the first to formalize rules for zero and negative numbers. His work Brahmasphutasiddhanta also explained methods for solving equations and working with integers, shaping mathematics for centuries to come

India was centuries ahead in mathematics. In the 7th century, Brahmagupta built on Aryabhata’s work and was the first to formalize rules for zero and negative numbers. His work Brahmasphutasiddhanta also explained methods for solving equations and working with integers, shaping mathematics for centuries to come

Wisdom Walk

18,294 views • 9 months ago

Deep learning. Large language models. Vast capabilities. ☁️💻💡 From chatbots to code generation, learn how #GenerativeAI is redefining #ML-powered capabilities—& how you can build & use large language on #AWS. #MachineLearning #AI 👉

Deep learning. Large language models. Vast capabilities. ☁️💻💡 From chatbots to code generation, learn how #GenerativeAI is redefining #ML-powered capabilities—& how you can build & use large language on #AWS. #MachineLearning #AI 👉

Amazon Web Services

113,319 views • 3 years ago

Can we synthesize 3D human-scene interactions without learning from any 3D data? Yes! Check out Lei Li's GenZI, a novel zero-shot approach to generating 3D interactions by distilling priors from large vision-language models.

Can we synthesize 3D human-scene interactions without learning from any 3D data? Yes! Check out Lei Li's GenZI, a novel zero-shot approach to generating 3D interactions by distilling priors from large vision-language models.

Angela Dai

106,939 views • 2 years ago

📁 Terence Tao, Fields Medal mathematician, says mathematics could become AI’s safest and most powerful domain. Language models can be brilliant or completely wrong, but in math every claim is forced through logic and can even be verified by proof assistants. Where other fields struggle with unreliability, mathematics can eliminate the noise and preserve only what is true.

📁 Terence Tao, Fields Medal mathematician, says mathematics could become AI’s safest and most powerful domain. Language models can be brilliant or completely wrong, but in math every claim is forced through logic and can even be verified by proof assistants. Where other fields struggle with unreliability, mathematics can eliminate the noise and preserve only what is true.

Jon Hernandez

80,288 views • 6 months ago

Yorubas only need a sound to help or destroy you. Our language is so deep mehn

Yorubas only need a sound to help or destroy you. Our language is so deep mehn

Bachelor of Idan

34,222 views • 9 months ago

we're turning University of Waterloo into a supercomputer! arceus is a cross-device distributed compute network for training large models, using model/tensor/pipeline parallelism. you can train anything, from deep neural networks to language models on the network. oss & deployment soon!

we're turning University of Waterloo into a supercomputer! arceus is a cross-device distributed compute network for training large models, using model/tensor/pipeline parallelism. you can train anything, from deep neural networks to language models on the network. oss & deployment soon!

rajan agarwal

35,720 views • 1 year ago

The Qwen model family cyber atlas: a visual walkthrough of how AI really evolved — from large language models to embodied intelligence. It all begins with large language models. Watch the full video below.

The Qwen model family cyber atlas: a visual walkthrough of how AI really evolved — from large language models to embodied intelligence. It all begins with large language models. Watch the full video below.

Tongyi Lab

4,191,058 views • 1 month ago

No language barriers. Just pure GOAL energy! In Nanjing, football is the universal language. Amine from Morocco and local Nanjing fans cheering together like old friends—that’s the magic of this city!

No language barriers. Just pure GOAL energy! In Nanjing, football is the universal language. Amine from Morocco and local Nanjing fans cheering together like old friends—that’s the magic of this city!

Discover Nanjing

12,230 views • 11 months ago

Day 4 in Observability Zero to Hero We look at How Observability Reduces MTTR(Mean Time to Resolution) I explain in this one 1. Production Incident Investigation Explained 2. Observability Maturity Models

Day 4 in Observability Zero to Hero We look at How Observability Reduces MTTR(Mean Time to Resolution) I explain in this one 1. Production Incident Investigation Explained 2. Observability Maturity Models

Jaydeep

17,644 views • 2 months ago

On Redacted, I explained how the “Kentucky family” in my opponent’s campaign ad turned out to be models from Ukraine!

On Redacted, I explained how the “Kentucky family” in my opponent’s campaign ad turned out to be models from Ukraine!

Thomas Massie for Congress

82,042 views • 8 months ago

In her Oxford Mathematics Public Lecture Erica Thompson focused on the inevitable biases and subjectivity of mathematical models. Which is a bit of a problem when you have audiences only too willing to not believe those models. Watch the full lecture:

In her Oxford Mathematics Public Lecture Erica Thompson focused on the inevitable biases and subjectivity of mathematical models. Which is a bit of a problem when you have audiences only too willing to not believe those models. Watch the full lecture:

Oxford Mathematics

12,498 views • 1 year ago

New research from Meta FAIR: Large Concept Models (LCM) is a fundamentally different paradigm for language modeling that decouples reasoning from language representation, inspired by how humans can plan high-level thoughts to communicate.

New research from Meta FAIR: Large Concept Models (LCM) is a fundamentally different paradigm for language modeling that decouples reasoning from language representation, inspired by how humans can plan high-level thoughts to communicate.

AI at Meta

531,765 views • 1 year ago

Mathematician Joel David says current AI models are basically zero help for mathematics They produce garbage answers, then argue they're correct when you point out the exact error "if i were talking to a person who argued like that, i'd stop talking to them"

Mathematician Joel David says current AI models are basically zero help for mathematics They produce garbage answers, then argue they're correct when you point out the exact error "if i were talking to a person who argued like that, i'd stop talking to them"

Haider.

1,754,725 views • 8 months ago

Introducing private AI image generation on your Mac. Generate images with leading and open weight models, from a private workspace. Zero data retention by default. No one looking at your prompts and images. Yours only. Open Source + MIT.

Introducing private AI image generation on your Mac. Generate images with leading and open weight models, from a private workspace. Zero data retention by default. No one looking at your prompts and images. Yours only. Open Source + MIT.

OpenSoftware

137,221 views • 1 month ago

Spike Lee explained how Michael Jackson used to have a really deep voice but only uses the fake thin voice to address people who aren’t very close to him

Spike Lee explained how Michael Jackson used to have a really deep voice but only uses the fake thin voice to address people who aren’t very close to him

FELIX 🇦🇷 🇪🇸

119,512 views • 3 months ago

Today is a good day to level up the baseline education in the XRP Community! I highly recommend Topics ranging from crypto basics, DeFi, AMM, Pathfinding, Autobridging, Trustlines and more explained in easy to understand language. For free and NO signup

Today is a good day to level up the baseline education in the XRP Community! I highly recommend Topics ranging from crypto basics, DeFi, AMM, Pathfinding, Autobridging, Trustlines and more explained in easy to understand language. For free and NO signup

Vet

50,324 views • 1 year ago

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

AK

290,517 views • 3 years ago

No agreement, no ceasefire and no peace deal will change the nature of these terrorists. Violence and repression remain the language of the IRGC. The only solution is to remove it from this world.

No agreement, no ceasefire and no peace deal will change the nature of these terrorists. Violence and repression remain the language of the IRGC. The only solution is to remove it from this world.

MEP Sebastian Tynkkynen

25,143 views • 2 months ago

From Emily Riehl on the #aboutlogic podcast (w/ Deniz Sarikaya): "I much prefer to interact with an autoformalisation agent than a large language model in discussing mathematics, because the large language models will feed you a lot of bullshit ..." "I came up with my own counterexample, and then I asked Harmonic's agent Aristotle to verify it for me in Lean as a kind of extra check that my counterexample was correct. I did not ask a large language model for this, because if they tell me it's correct, that gives me no assurance ..." "Aristotle was able to confirm that it is a valid counterexample."

From Emily Riehl on the #aboutlogic podcast (w/ Deniz Sarikaya): "I much prefer to interact with an autoformalisation agent than a large language model in discussing mathematics, because the large language models will feed you a lot of bullshit ..." "I came up with my own counterexample, and then I asked Harmonic's agent Aristotle to verify it for me in Lean as a kind of extra check that my counterexample was correct. I did not ask a large language model for this, because if they tell me it's correct, that gives me no assurance ..." "Aristotle was able to confirm that it is a valid counterexample."

Harmonic

41,317 views • 1 month ago