Deep Learning 01

 0    23 fiche    mszzemanek
Télécharger mP3 Imprimer jouer consultez
 
question réponse
accomplish
We describe how to accomplish these goals by specifying a model that represents certain beliefs
commencer à apprendre
osiągać
throughout
Linear algebra is a branch of mathematics that is widely used throughout science and engineering.
commencer à apprendre
poprzez
prerequisites
the key linear algebra prerequisites
commencer à apprendre
warunki wstępne
slope
the slope of the line
commencer à apprendre
stok / nachylenie
nachylenie linii
can be thought of
scalar can be thought of as a matrix with only a single entry
commencer à apprendre
można pomyśleć
to yield
We allow the addition of matrix and a vector, yielding another matrix
commencer à apprendre
wydawać, dawać
commutative
Matrix multiplication is not commutative
commencer à apprendre
przemienny
undesirable
commencer à apprendre
niepożądany
we can derive
commencer à apprendre
możemy wprowadzić
to staring
Sunset came; I stared at the México sky. Isn’t nature splendid
commencer à apprendre
gapić się
exclusive to
It’s not exclusive to machine learning
commencer à apprendre
wyłącznie dla
consecutive
Where tokens are groups of N consecutive words
commencer à apprendre
kolejny
discarding
and those that treat input words as a set, discarding their original order
commencer à apprendre
odrzucanie
discrepancy
you would face the risk of introducing small preprocessing discrepancies that would hurt the model’s accuracy.
commencer à apprendre
rozbieżność
reshuffling
Even within a given language, you can typically say the same thing in different ways by reshuffling the words a bit
commencer à apprendre
przetasowania
is an interesting one
The problem of order in natural language is an interesting one:
commencer à apprendre
jest ciekawa
Even further
Even further, if you fully randomize the words in a short sentence
commencer à apprendre
Nawet dalej / co więcej
pivotal
How to represent word order is the pivotal question
commencer à apprendre
kluczowy
from which spring
from which different kinds of NLP architectures spring.
commencer à apprendre
z którego źródła?
how/when to leverage which
Let’s see how they work, and when to leverage which.
commencer à apprendre
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.
commencer à apprendre
bez wykorzystywania
How could we address this?
commencer à apprendre
Jak moglibyśmy się tym zająć?
sparse, sparsity
commencer à apprendre
rzadki, rzadkość

Vous devez vous connecter pour poster un commentaire.