Deep Learning 01

 0    23 adatlap    mszzemanek
letöltés mp3 Nyomtatás játszik ellenőrizze magát
 
kérdés válasz
accomplish
We describe how to accomplish these goals by specifying a model that represents certain beliefs
kezdjen tanulni
osiągać
throughout
Linear algebra is a branch of mathematics that is widely used throughout science and engineering.
kezdjen tanulni
poprzez
prerequisites
the key linear algebra prerequisites
kezdjen tanulni
warunki wstępne
slope
the slope of the line
kezdjen tanulni
stok / nachylenie
nachylenie linii
can be thought of
scalar can be thought of as a matrix with only a single entry
kezdjen tanulni
można pomyśleć
to yield
We allow the addition of matrix and a vector, yielding another matrix
kezdjen tanulni
wydawać, dawać
commutative
Matrix multiplication is not commutative
kezdjen tanulni
przemienny
undesirable
kezdjen tanulni
niepożądany
we can derive
kezdjen tanulni
możemy wprowadzić
to staring
Sunset came; I stared at the México sky. Isn’t nature splendid
kezdjen tanulni
gapić się
exclusive to
It’s not exclusive to machine learning
kezdjen tanulni
wyłącznie dla
consecutive
Where tokens are groups of N consecutive words
kezdjen tanulni
kolejny
discarding
and those that treat input words as a set, discarding their original order
kezdjen tanulni
odrzucanie
discrepancy
you would face the risk of introducing small preprocessing discrepancies that would hurt the model’s accuracy.
kezdjen tanulni
rozbieżność
reshuffling
Even within a given language, you can typically say the same thing in different ways by reshuffling the words a bit
kezdjen tanulni
przetasowania
is an interesting one
The problem of order in natural language is an interesting one:
kezdjen tanulni
jest ciekawa
Even further
Even further, if you fully randomize the words in a short sentence
kezdjen tanulni
Nawet dalej / co więcej
pivotal
How to represent word order is the pivotal question
kezdjen tanulni
kluczowy
from which spring
from which different kinds of NLP architectures spring.
kezdjen tanulni
z którego źródła?
how/when to leverage which
Let’s see how they work, and when to leverage which.
kezdjen tanulni
jak/kiedy wykorzystać które?
without leveraging
Meanwhile, the best score that can be achieved on this dataset without leveraging external data is around 95% test accuracy.
kezdjen tanulni
bez wykorzystywania
How could we address this?
kezdjen tanulni
Jak moglibyśmy się tym zająć?
sparse, sparsity
kezdjen tanulni
rzadki, rzadkość

Kommentár közzétételéhez be kell jelentkeznie.