[SR] Week 1 translations #720
Conversation
Great! :) |
There was a problem hiding this comment.
We should synchronize on do we use transcription or not - there is McCullough, LeCun and then there is Fukušima and Križevski (not Fukushima and Krizhevsky). Same thing for model names. I suggest we keep them as original names, since I guess someone might want to look them up on Google Scholar or something. Even better, add \emph{} on names, so in case we later decide on cyrillic alphabet, we can easily avoid their names being converted to cyrillic.
Co-authored-by: Dusan Svilarkovic <[email protected]>
Co-authored-by: Dusan Svilarkovic <[email protected]>
Co-authored-by: Dusan Svilarkovic <[email protected]>
Co-authored-by: Dusan Svilarkovic <[email protected]>
Co-authored-by: Dusan Svilarkovic <[email protected]>
Co-authored-by: Dusan Svilarkovic <[email protected]>
I agree, maybe we should check what others think and then update? |
Atcold
dismissed
their stale review
This was a technical review and not based on the content.
|
|
||
| <!--Fukushima (1982) built a neural net (NN) that worked the same way as the brain, based on two concepts. First, neurons are replicated across the visual field. Second, there are complex cells that pool the information from simple cells (orientation-selective units). As a result, the shift of the picture will change the activation of simple cells, but will not influence the integrated activation of the complex cell (convolutional pooling). | ||
| --> | ||
| Fukušima je 1982. godine napravio neuronsku mrežu koja je radila na isti način kao i mozak, bazirano na 2 koncepta. Prvo, neuroni su postavljeni po celom vidnom polju. Drugo, postoje kompleksne ćelije koje agregiraju informacije iz jednostavnih ćelija (jedinica koje reaguju na orijentaciju). Kao rezultat, pomeraj slike će uticati na aktivacije jednostavnih ćelija, ali neće uticati na agregiranu aktivaciju komplikovane ćelije (agregiranje konvolucijom). |
|
|
||
| <!--LeCun (1990) used backprop to train a CNN to recognize handwritten digits. There is a demo from 1992 where the algorithm recognizes the digits of any style. Doing character/pattern recognition using a model that is trained end-to-end was new at that time. Previously, people had used feature extractors with a supervised model on top. | ||
| --> | ||
| LeCun je 1990. godine iskoristio propagaciju unazad da obuči konvolucionu neuronsku mrežu da prepozna rukom pisane cifre. Postoji video iz 1992. gde algoritam prepoznaje cifre napisane različitim stilovima. Prepoznavanje karaktera / oblika koristeći model koji rešava problem od početka do kraja je bilo novo u to vreme. Ranije je bilo neophodno izvlačenje obeležja pre modela nadgledanog učenja. |
There was a problem hiding this comment.
karaktera -> slova
je bilo novo u to vreme -> predstavljala je inovaciju u to vreme
izvlačenje obeležja: not sure if this is immediately understandable as feature extractor
No description provided.