Generative Query Network (GQN) - Revision history

BPeat at 20:53, 28 April 2024

2024-04-28T20:53:36Z

BPeat at 20:51, 28 April 2024

2024-04-28T20:51:40Z

BPeat: Text replacement - "* Conversational AI ... ChatGPT | OpenAI ... Bing | Microsoft ... Bard | Google ... Claude | Anthropic ... Perplexity ... You ... Ernie | Baidu" to "* Conversational AI ... [[C...

2024-03-16T15:22:39Z

BPeat at 23:55, 8 September 2023

2023-09-08T23:55:58Z

BPeat at 19:04, 2 September 2023

2023-09-02T19:04:07Z

BPeat at 21:40, 13 July 2023

2023-07-13T21:40:35Z

BPeat at 02:32, 12 July 2023

2023-07-12T02:32:18Z

BPeat at 17:04, 15 April 2023

2023-04-15T17:04:49Z

BPeat: Text replacement - "BingAI" to "Bing"

2023-03-31T01:31:29Z

Text replacement - "BingAI" to "Bing"

BPeat at 01:58, 25 March 2023

2023-03-25T01:58:15Z

@@ Line 26: / Line 26: @@
 A framework within which machines learn to perceive their surroundings by training only on data obtained by themselves as they move around scenes. Much like infants and animals, the GQN learns by trying to make sense of its observations of the world around it. In doing so, the GQN learns about plausible scenes and their geometrical properties, without any human labelling of the contents of scenes. The GQN model is composed of two parts: a representation network and a generation network. The representation network takes the [[Agents|agent]]'s observations as its input and produces a representation (a vector) which describes the underlying scene. The generation network then predicts (‘imagines’) the scene from a previously unobserved viewpoint. [https://deepmind.com/documents/211/Neural_Scene_Representation_and_Rendering_preprint.pdf Neural Scene Representation and Rendering | Science Reprint]
-One half of the system is its “representation” part, which can observe a given 3D scene from some angle, encoding it in a complex mathematical form called a vector. Then there’s the “generative” part, which, based only on the vectors created earlier, predicts what a different part of the scene would look like.  “It was not at all clear that a neural network could ever learn to create images in such a precise and controlled manner,” said lead author of the paper, Ali Eslami, in a release accompanying the paper. “However we found that sufficiently deep networks can learn about [[Perspective]], occlusion and lighting, without any human engineering. This was a super surprising finding.”  It also allows the system to accurately recreate a 3D object from a single viewpoint, such as the blocks shown here:  [https://big4all.org/2018/06/14/bwuduljk3vm/ AI edges closer to understanding 3D space the way we do | BIG4ALL.ORG]
+One half of the system is its “representation” part, which can observe a given 3D scene from some angle, encoding it in a complex mathematical form called a vector. Then there’s the “generative” part, which, based only on the vectors created earlier, predicts what a different part of the scene would look like.  “It was not at all clear that a neural network could ever learn to create images in such a precise and controlled manner,” said lead author of the paper, Ali Eslami, in a release accompanying the paper. “However we found that sufficiently deep networks can learn about [[perspective]], occlusion and lighting, without any human engineering. This was a super surprising finding.”  It also allows the system to accurately recreate a 3D object from a single viewpoint, such as the blocks shown here:  [https://big4all.org/2018/06/14/bwuduljk3vm/ AI edges closer to understanding 3D space the way we do | BIG4ALL.ORG]
 https://i1.wp.com/techcrunch.com/wp-content/uploads/2018/06/gif_2.gif

@@ Line 19: / Line 19: @@
 * [[Artificial General Intelligence (AGI) to Singularity]] ... [[Inside Out - Curious Optimistic Reasoning| Curious Reasoning]] ... [[Emergence]] ... [[Moonshots]] ... [[Explainable / Interpretable AI|Explainable AI]] ...  [[Algorithm Administration#Automated Learning|Automated Learning]]
 * [[What is Artificial Intelligence (AI)? | Artificial Intelligence (AI)]] ... [[Generative AI]] ... [[Machine Learning (ML)]] ... [[Deep Learning]] ... [[Neural Network]] ... [[Reinforcement Learning (RL)|Reinforcement]] ... [[Learning Techniques]]
 * [[Conversational AI]] ... [[ChatGPT]] | [[OpenAI]] ... [[Bing/Copilot]] | [[Microsoft]] ... [[Gemini]] | [[Google]] ... [[Claude]] | [[Anthropic]] ... [[Perplexity]] ... [[You]] ... [[phind]] ... [[Ernie]] | [[Baidu]]
 * [https://science.sciencemag.org/content/360/6394/1204.full Neural scene representation and rendering | Science]
@@ Line 25: / Line 26: @@
 A framework within which machines learn to perceive their surroundings by training only on data obtained by themselves as they move around scenes. Much like infants and animals, the GQN learns by trying to make sense of its observations of the world around it. In doing so, the GQN learns about plausible scenes and their geometrical properties, without any human labelling of the contents of scenes. The GQN model is composed of two parts: a representation network and a generation network. The representation network takes the [[Agents|agent]]'s observations as its input and produces a representation (a vector) which describes the underlying scene. The generation network then predicts (‘imagines’) the scene from a previously unobserved viewpoint. [https://deepmind.com/documents/211/Neural_Scene_Representation_and_Rendering_preprint.pdf Neural Scene Representation and Rendering | Science Reprint]
-One half of the system is its “representation” part, which can observe a given 3D scene from some angle, encoding it in a complex mathematical form called a vector. Then there’s the “generative” part, which, based only on the vectors created earlier, predicts what a different part of the scene would look like.  “It was not at all clear that a neural network could ever learn to create images in such a precise and controlled manner,” said lead author of the paper, Ali Eslami, in a release accompanying the paper. “However we found that sufficiently deep networks can learn about perspective, occlusion and lighting, without any human engineering. This was a super surprising finding.”  It also allows the system to accurately recreate a 3D object from a single viewpoint, such as the blocks shown here:  [https://big4all.org/2018/06/14/bwuduljk3vm/ AI edges closer to understanding 3D space the way we do | BIG4ALL.ORG]
+One half of the system is its “representation” part, which can observe a given 3D scene from some angle, encoding it in a complex mathematical form called a vector. Then there’s the “generative” part, which, based only on the vectors created earlier, predicts what a different part of the scene would look like.  “It was not at all clear that a neural network could ever learn to create images in such a precise and controlled manner,” said lead author of the paper, Ali Eslami, in a release accompanying the paper. “However we found that sufficiently deep networks can learn about [[Perspective]], occlusion and lighting, without any human engineering. This was a super surprising finding.”  It also allows the system to accurately recreate a 3D object from a single viewpoint, such as the blocks shown here:  [https://big4all.org/2018/06/14/bwuduljk3vm/ AI edges closer to understanding 3D space the way we do | BIG4ALL.ORG]
 https://i1.wp.com/techcrunch.com/wp-content/uploads/2018/06/gif_2.gif

@@ Line 19: / Line 19: @@
 * [[Artificial General Intelligence (AGI) to Singularity]] ... [[Inside Out - Curious Optimistic Reasoning| Curious Reasoning]] ... [[Emergence]] ... [[Moonshots]] ... [[Explainable / Interpretable AI|Explainable AI]] ...  [[Algorithm Administration#Automated Learning|Automated Learning]]
 * [[What is Artificial Intelligence (AI)? | Artificial Intelligence (AI)]] ... [[Generative AI]] ... [[Machine Learning (ML)]] ... [[Deep Learning]] ... [[Neural Network]] ... [[Reinforcement Learning (RL)|Reinforcement]] ... [[Learning Techniques]]
-* [[Conversational AI]] ... [[ChatGPT]] | [[OpenAI]] ... [[Bing]] | [[Microsoft]] ... [[Bard]] | [[Google]] ... [[Claude]] | [[Anthropic]] ... [[Perplexity]] ... [[You]] ... [[Ernie]] | [[Baidu]]
+* [[Conversational AI]] ... [[ChatGPT]] | [[OpenAI]] ... [[Bing/Copilot]] | [[Microsoft]] ... [[Gemini]] | [[Google]] ... [[Claude]] | [[Anthropic]] ... [[Perplexity]] ... [[You]] ... [[phind]] ... [[Ernie]] | [[Baidu]]
 * [https://science.sciencemag.org/content/360/6394/1204.full Neural scene representation and rendering | Science]

@@ Line 17: / Line 17: @@
 [https://www.google.com/search?q=generative+query+network+GQN+reinforcement+learning+model+machine+learning+ML+artificial+intelligence ...Google search]
-* [[Singularity]] ... [[Artificial Consciousness / Sentience|Sentience]] ... [[Artificial General Intelligence (AGI)| AGI]] ... [[Inside Out - Curious Optimistic Reasoning| Curious Reasoning]] ... [[Emergence]] ... [[Moonshots]] ... [[Explainable / Interpretable AI|Explainable AI]] ... [[Algorithm Administration#Automated Learning|Automated Learning]]
+* [[Artificial General Intelligence (AGI) to Singularity]] ... [[Inside Out - Curious Optimistic Reasoning| Curious Reasoning]] ... [[Emergence]] ... [[Moonshots]] ... [[Explainable / Interpretable AI|Explainable AI]] ...  [[Algorithm Administration#Automated Learning|Automated Learning]]
 * [[What is Artificial Intelligence (AI)? | Artificial Intelligence (AI)]] ... [[Generative AI]] ... [[Machine Learning (ML)]] ... [[Deep Learning]] ... [[Neural Network]] ... [[Reinforcement Learning (RL)|Reinforcement]] ... [[Learning Techniques]]
 * [[Conversational AI]] ... [[ChatGPT]] | [[OpenAI]] ... [[Bing]] | [[Microsoft]] ... [[Bard]] | [[Google]] ... [[Claude]] | [[Anthropic]] ... [[Perplexity]] ... [[You]] ... [[Ernie]] | [[Baidu]]

@@ Line 18: / Line 18: @@
 * [[Singularity]] ... [[Artificial Consciousness / Sentience|Sentience]] ... [[Artificial General Intelligence (AGI)| AGI]] ... [[Inside Out - Curious Optimistic Reasoning| Curious Reasoning]] ... [[Emergence]] ... [[Moonshots]] ... [[Explainable / Interpretable AI|Explainable AI]] ... [[Algorithm Administration#Automated Learning|Automated Learning]]
-* [[Reinforcement Learning (RL)]]
+* [[What is Artificial Intelligence (AI)? | Artificial Intelligence (AI)]] ... [[Generative AI]] ... [[Machine Learning (ML)]] ... [[Deep Learning]] ... [[Neural Network]] ... [[Reinforcement Learning (RL)|Reinforcement]] ... [[Learning Techniques]]
 * [https://science.sciencemag.org/content/360/6394/1204.full Neural scene representation and rendering | Science]

← Older revision		Revision as of 21:40, 13 July 2023
Line 24:		Line 24:

	A framework within which machines learn to perceive their surroundings by training only on data obtained by themselves as they move around scenes. Much like infants and animals, the GQN learns by trying to make sense of its observations of the world around it. In doing so, the GQN learns about plausible scenes and their geometrical properties, without any human labelling of the contents of scenes. The GQN model is composed of two parts: a representation network and a generation network. The representation network takes the [[Agents\|agent]]'s observations as its input and produces a representation (a vector) which describes the underlying scene. The generation network then predicts (‘imagines’) the scene from a previously unobserved viewpoint. [https://deepmind.com/documents/211/Neural_Scene_Representation_and_Rendering_preprint.pdf Neural Scene Representation and Rendering \| Science Reprint]		A framework within which machines learn to perceive their surroundings by training only on data obtained by themselves as they move around scenes. Much like infants and animals, the GQN learns by trying to make sense of its observations of the world around it. In doing so, the GQN learns about plausible scenes and their geometrical properties, without any human labelling of the contents of scenes. The GQN model is composed of two parts: a representation network and a generation network. The representation network takes the [[Agents\|agent]]'s observations as its input and produces a representation (a vector) which describes the underlying scene. The generation network then predicts (‘imagines’) the scene from a previously unobserved viewpoint. [https://deepmind.com/documents/211/Neural_Scene_Representation_and_Rendering_preprint.pdf Neural Scene Representation and Rendering \| Science Reprint]
−
−	~~https://i0.wp.com/big4all.org/wp-content/uploads/2018/06/example_gqn.png~~

	One half of the system is its “representation” part, which can observe a given 3D scene from some angle, encoding it in a complex mathematical form called a vector. Then there’s the “generative” part, which, based only on the vectors created earlier, predicts what a different part of the scene would look like. “It was not at all clear that a neural network could ever learn to create images in such a precise and controlled manner,” said lead author of the paper, Ali Eslami, in a release accompanying the paper. “However we found that sufficiently deep networks can learn about perspective, occlusion and lighting, without any human engineering. This was a super surprising finding.” It also allows the system to accurately recreate a 3D object from a single viewpoint, such as the blocks shown here: [https://big4all.org/2018/06/14/bwuduljk3vm/ AI edges closer to understanding 3D space the way we do \| BIG4ALL.ORG]		One half of the system is its “representation” part, which can observe a given 3D scene from some angle, encoding it in a complex mathematical form called a vector. Then there’s the “generative” part, which, based only on the vectors created earlier, predicts what a different part of the scene would look like. “It was not at all clear that a neural network could ever learn to create images in such a precise and controlled manner,” said lead author of the paper, Ali Eslami, in a release accompanying the paper. “However we found that sufficiently deep networks can learn about perspective, occlusion and lighting, without any human engineering. This was a super surprising finding.” It also allows the system to accurately recreate a 3D object from a single viewpoint, such as the blocks shown here: [https://big4all.org/2018/06/14/bwuduljk3vm/ AI edges closer to understanding 3D space the way we do \| BIG4ALL.ORG]

@@ Line 2: / Line 2: @@
 |title=PRIMO.ai
 |titlemode=append
-|keywords=artificial, intelligence, machine, learning, models, algorithms, data, singularity, moonshot, Tensorflow, Google, Nvidia, Microsoft, Azure, Amazon, AWS
+|keywords=ChatGPT, artificial, intelligence, machine, learning, GPT-4, GPT-5, NLP, NLG, NLC, NLU, models, data, singularity, moonshot, Sentience, AGI, Emergence, Moonshot, Explainable, TensorFlow, Google, Nvidia, Microsoft, Azure, Amazon, AWS, Hugging Face, OpenAI, Tensorflow, OpenAI, Google, Nvidia, Microsoft, Azure, Amazon, AWS, Meta, LLM, metaverse, assistants, agents, digital twin, IoT, Transhumanism, Immersive Reality, Generative AI, Conversational AI, Perplexity, Bing, You, Bard, Ernie, prompt Engineering LangChain, Video/Image, Vision, End-to-End Speech, Synthesize Speech, Speech Recognition, Stanford, MIT |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools
 |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools
 }}
 [https://www.youtube.com/results?search_query=generative+query+network+GQN+reinforcement+learning+model YouTube search...]
 [https://www.google.com/search?q=generative+query+network+GQN+reinforcement+learning+model+machine+learning+ML+artificial+intelligence ...Google search]
-* [[Inside Out - Curious Optimistic Reasoning]]
+* [[Singularity]] ... [[Artificial Consciousness / Sentience|Sentience]] ... [[Artificial General Intelligence (AGI)| AGI]] ... [[Inside Out - Curious Optimistic Reasoning| Curious Reasoning]] ... [[Emergence]] ... [[Moonshots]] ... [[Explainable / Interpretable AI|Explainable AI]] ... [[Algorithm Administration#Automated Learning|Automated Learning]]
 * [[Reinforcement Learning (RL)]]
 * [https://science.sciencemag.org/content/360/6394/1204.full Neural scene representation and rendering | Science]
-* [[Generative AI]]  ... [[Conversational AI]] ... [[OpenAI]]'s [[ChatGPT]] ... [[Perplexity]]  ... [[Microsoft]]'s [[Bing]] ... [[You]] ...[[Google]]'s [[Bard]] ... [[Baidu]]'s [[Ernie]]
+* [[Generative AI]] ... [[Conversational AI]] ... [[ChatGPT]] | [[OpenAI]] ... [[Bing]] | [[Microsoft]] ... [[Bard]] | [[Google]] ... [[Claude]] | [[Anthropic]] ... [[Perplexity]] ... [[You]] ... [[Ernie]] | [[Baidu]]

@@ Line 11: / Line 11: @@
 * [[Reinforcement Learning (RL)]]
 * [https://science.sciencemag.org/content/360/6394/1204.full Neural scene representation and rendering | Science]
-* [[Generative AI]]  ... [[OpenAI]]'s [[ChatGPT]] ... [[Perplexity]]  ... [[Microsoft]]'s [[BingAI]] ... [[You]] ...[[Google]]'s [[Bard]] ... [[Baidu]]'s [[Ernie]]
+* [[Generative AI]]  ... [[OpenAI]]'s [[ChatGPT]] ... [[Perplexity]]  ... [[Microsoft]]'s [[Bing]] ... [[You]] ...[[Google]]'s [[Bard]] ... [[Baidu]]'s [[Ernie]]