Discover and read the best of Twitter Threads about #Inference
Most recents (4)
6 Sources of Knowledge According to Ancient Indian Philosophies
-
A Brief Thread on Pramana-s (Sources or Evidence of Knowledge)
(1/8)
-
A Brief Thread on Pramana-s (Sources or Evidence of Knowledge)
(1/8)
Pratyakṣa (Perception)
This is the most direct form of knowledge, obtained through the five senses (sight, hearing, taste, smell, touch) or the mind. It's considered to be the most immediate and reliable source of knowledge. #Pratyaksha #Perception
(2/8)
This is the most direct form of knowledge, obtained through the five senses (sight, hearing, taste, smell, touch) or the mind. It's considered to be the most immediate and reliable source of knowledge. #Pratyaksha #Perception
(2/8)
Anumāna (Inference):
Inference is the process of deriving conclusions based on perceived evidence or premises.
It's a critical tool for developing knowledge when direct perception isn't possible and is widely used in philosophical debates. #Anumana #Inference
(3/8)
Inference is the process of deriving conclusions based on perceived evidence or premises.
It's a critical tool for developing knowledge when direct perception isn't possible and is widely used in philosophical debates. #Anumana #Inference
(3/8)
🚀 We are live! Here is the correct streaming link for all of today's discussions and performances, starting with a panel on complex time with David Krakauer, James Gleick, Ted Chiang, and David Wolpert in a few moments (measured linearly...):
#IPFest
#IPFest
"One of the ideas we had with #InterPlanetary was, 'What would it take to make science hedonistic? And instead of telling people to do it, you'd have to tell people to STOP doing it?"
- SFI President David Krakauer sets the tone for this weekend's celebrations
#IPFest
- SFI President David Krakauer sets the tone for this weekend's celebrations
#IPFest
David Krakauer: "Do you have a favorite model or metaphor for #time?"
@JamesGleick: "You've already mentioned a river; that's everybody's favorite. Borges said time is a tiger. People talk about it as a thread. We ONLY talk about time in metaphors."
@JamesGleick: "You've already mentioned a river; that's everybody's favorite. Borges said time is a tiger. People talk about it as a thread. We ONLY talk about time in metaphors."
"#Imitation vs #Innovation: Large #Language and Image Models as Cultural #Technologies"
Today's Seminar by SFI External Prof @AlisonGopnik (@UCBerkeley)
Streaming now:
Follow our 🧵 for live coverage.
Today's Seminar by SFI External Prof @AlisonGopnik (@UCBerkeley)
Streaming now:
Follow our 🧵 for live coverage.
"Today you hear people talking about 'AN #AI' or 'THE AI.' Even 15 years ago we would not have heard this; we just heard 'AI.'"
@AlisonGopnik on the history of thought on the #intelligence (or lack thereof) of #simulacra, linked to the convincing foolery of "double-talk artists":
@AlisonGopnik on the history of thought on the #intelligence (or lack thereof) of #simulacra, linked to the convincing foolery of "double-talk artists":
"We should think about these large #AI models as cultural technologies: tools that allow one generation of humans to learn from another & do this repeatedly over a long period of time. What are some examples?"
@AlisonGopnik suggests a continuity between #GPT3 & language itself:
@AlisonGopnik suggests a continuity between #GPT3 & language itself:
#Highlights2021 for me: our #survey on efficient processing of #sparse and compressed tensors of #ML/#DNN models on #hardware accelerators published in @ProceedingsIEEE.
Paper: dx.doi.org/10.1109/JPROC.…
arXiv: arxiv.org/abs/2007.00864
RT/sharing appreciated. 🧵
Paper: dx.doi.org/10.1109/JPROC.…
arXiv: arxiv.org/abs/2007.00864
RT/sharing appreciated. 🧵
Context: Tensors of ML/DNN are compressed by leveraging #sparsity, #quantization, shape reduction. We summarize several such sources of sparsity & compression (§3). Sparsity is induced in structure while pruning & it is unstructured inherently for various applications or sources.
Likewise, leveraging value similarity or approximate operations could yield irregularity in processing. Also, techniques for size-reduction make tensors asymmetric-shaped. Hence, special mechanisms can be required for efficient processing of sparse and irregular computations.
