Deep Learning 01

 0    23 flashcards    mszzemanek
download mp3 print play test yourself
 
Question Answer
accomplish
We describe how to accomplish these goals by specifying a model that represents certain beliefs
start learning
osiągać
throughout
Linear algebra is a branch of mathematics that is widely used throughout science and engineering.
start learning
poprzez
prerequisites
the key linear algebra prerequisites
start learning
warunki wstępne
slope
the slope of the line
start learning
stok / nachylenie
nachylenie linii
can be thought of
scalar can be thought of as a matrix with only a single entry
start learning
można pomyśleć
to yield
We allow the addition of matrix and a vector, yielding another matrix
start learning
wydawać, dawać
commutative
Matrix multiplication is not commutative
start learning
przemienny
undesirable
start learning
niepożądany
we can derive
start learning
możemy wprowadzić
to staring
Sunset came; I stared at the México sky. Isn’t nature splendid
start learning
gapić się
exclusive to
It’s not exclusive to machine learning
start learning
wyłącznie dla
consecutive
Where tokens are groups of N consecutive words
start learning
kolejny
discarding
and those that treat input words as a set, discarding their original order
start learning
odrzucanie
discrepancy
you would face the risk of introducing small preprocessing discrepancies that would hurt the model’s accuracy.
start learning
rozbieżność
reshuffling
Even within a given language, you can typically say the same thing in different ways by reshuffling the words a bit
start learning
przetasowania
is an interesting one
The problem of order in natural language is an interesting one:
start learning
jest ciekawa
Even further
Even further, if you fully randomize the words in a short sentence
start learning
Nawet dalej / co więcej
pivotal
How to represent word order is the pivotal question
start learning
kluczowy
from which spring
from which different kinds of NLP architectures spring.
start learning
z którego źródła?
how/when to leverage which
Let’s see how they work, and when to leverage which.
start learning
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.
start learning
bez wykorzystywania
How could we address this?
start learning
Jak moglibyśmy się tym zająć?
sparse, sparsity
start learning
rzadki, rzadkość

You must sign in to write a comment