Well, I'm starting to hate all these new words and phrases that we've been fed.
It's just flippin our notes upside down. Some are the same thing like graph=NN,
some are completely useless. For example ML, ASI, Induction, graphs, epoch,
iterations, batches, converge, blackbox, axon, RL, papers and what's in them,
mapping, NLP, meta programming, GANs, Hopfields, tecoGAN, and phrases too like
"Given an unsupervised corpus of tokens U = {u1, . . . , un}, we use a standard
language modeling
objective to maximize the following likelihood:
L1(U) = X
i
log P(ui
|ui−k, . . . , ui−1; Θ)" and "our architecture uses a dense
connectivity pattern which does not encode the 2D spatial
structure of images".
I'm starting to switch to common words/ phrases, which make me and my readers
more connected to the truer meaning of the technology, and take much less time
to understand the work.
------------------------------------------
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/T0291e6571222d56c-M8c1c4b4ba7e2c6fffbd63469
Delivery options: https://agi.topicbox.com/groups/agi/subscription
