Discover and read the best of Twitter Threads about #DNN
Most recents (3)
The impressive deep pattern recognition abilities of #DNN's such as #LLM's are sometimes confused for reasoning abilities
I can learn to guess, with high accuracy, whether a SAT instance is satisfiable or not, but this not the same as knowing how to solve SAT. Let me explain. 1/
I can learn to guess, with high accuracy, whether a SAT instance is satisfiable or not, but this not the same as knowing how to solve SAT. Let me explain. 1/
Suppose you train a learner with a large number of Boolean 3-SAT instances labeled with whether or not they are satisfiable. There is no reason to doubt that a modern #DNN-based leaner will manage to learn deep features corresponding to the γ ratio-- #clauses/#variable .. 2/
..and armed with γ, it can also essentially figure out the sharp-threshold phenomenon w.r.t. to γ, and should be able to predict with high certainty that the γ < 4.3 are satisfiable and γ > 4.3 are unsatisfiable. 3/ 
Thank you to @BloorStreetCap for yesterday's insightful #uranium discussion with some of the pioneers of the industry. A fantastic line up with in depth insight into all aspects of the #uranium sector.
Some of our highlights can be found the the thread below:
Some of our highlights can be found the the thread below:
1/ “The world is recognising the science of nuclear power, not the false ideology.” – #NexGen CEO
“Price of #equities is screaming buy relative to the #spot price” – @uraniuminsider
“We’re on the cusp of a really really big move here [spot price]” – @UraniumEnergy
“Price of #equities is screaming buy relative to the #spot price” – @uraniuminsider
“We’re on the cusp of a really really big move here [spot price]” – @UraniumEnergy
2/ #Sprott are seeing growing #institutional and #FO interest in the #uranium space. Very early stages of broad adoption by generalist #investors. Ciampaglia believes we are ‘just starting the second inning of this uranium cycle’.
#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.
