Return Styles: Pseud0ch, Terminal, Valhalla, NES, Geocities, Blue Moon.

Pages: 1-

My Experience with SICP

Name: George Onsom. Shit 2014-06-06 0:11

; Alyssa P. Hacker doesn't see why if needs to be provided as a special form.
; "Why can't I just define it as an ordinary procedure in terms of cond?" she
; asks. Alyssa's friend Eva Lu Ator claims this can be done, and she defines a
; new version of if:

; (define (new-if predicate then-clause else-clause)
; (cond (predicate then-clause)
; (else else-clause)))

; Eva demonstrates the program for Alyssa:

; (new-if (= 2 3) 0 5)
; 5

; (new-if (= 1 1) 0 5)
; 0

; Delighted, Alyssa uses new-if to rewrite the square-root program:

; (define (sqrt-iter guess x)
; (new-if (good-enough? guess x)
; guess
; (sqrt-iter (improve guess x) x)))

; What happens when Alyssa attempts to use this to compute square roots?
; Explain.

What the fuck is your problem you stupid monkey? Take your fucking monkey hat
off your dumb Jewish ass and quit stressing me over fucking evaluation order
and write a fucking decent exercise for once. I wasn't happy with your
applicative-order v.s. normal-order bullshit and I'm not happy with this.

The operands that match 'then-clause' and 'else-clause' will be evaluated
before new-if is evaluated. This is because they're defined as procedures, not
syntax. How many more fucking exercise questions are you going to have that are
oriented around this same fucking concept? I get it. I'm not a stupid bitch
like Alyssa or Eva. You just need to face the facts, get this feminist bullshit
out of your head, and tell Alyssa and Eva to go back in the kitchen, and leave
programming to the men. That way you can assume that the reader has the
intelligence of the man and you might be able to write a few decent exercises
instead of elaborating on the same bullshit over and over. Note that I'm doing
you the same courtesy, as I've come to the realisation that, from sitting
around in a university all day, wearing a fucking monkey hat, your testosterone
levels have surely depleted to the level of a female, and thus you need to be
explained things like a female. Now quit wasting my time with these bullshit
exercises. Tired of this shit.

And, I repeat, take your fucking monkey hat off, you bloody circus freak.

Name: Anonymous 2014-06-06 0:56

>>1

Alyssa P. Hacker doesn't see why if needs to be provided as a special form.
Tell Alyssa she should go back to her retarded Haskell.

Name: Anonymous 2014-06-06 1:06

This site is actually pretty shitty and none of you know jack shit about programming let alone computer science.

Name: Anonymous 2014-06-06 1:07

You geniuses still cant get over a fucking introductory book. What a bunch of tryhard posers.

Name: Anonymous 2014-06-06 1:16

>>2
gay

Name: Anonymous 2014-06-06 1:57

>>4
Do you even know how to derive the value of an endotensor that is closed under its parent eigenfold? No? Then go scrub my toilet.

Name: Anonymous 2014-06-06 1:59

>>4
aww... I had a go at using RBM's as a Recurrent / Forward-encoder network.. It kind of succeeded at training multiple side-stacked layers concurrently, using shared weights. (Usually you train one layer at a time with RBM or it goes a bit haywire =)

It wasn't a particularly good series to test with though =/

Name: Anonymous 2014-06-06 2:20

The other trick was to use Gradient Splicing =D, which allows all sorts of non-auto-encodings =)
ie, you can give a semi-blank input and splice the target onto the input gradient for blind reconstruction ^^ or input t-1 and splice target t

Name: Anonymous 2014-06-06 2:24

>>8

Can you hint how to do deep learning without hardcoding what is important? Like when you do OCR you have to manually specify lines are important, so basically the first layer parses all kinds of lines, while second parses their permutations and topology. Is it possible to design a system, that would guess itself what it should look for?

Name: Anonymous 2014-06-06 2:33

It even has hidden->hidden connections, because i left a large blank in the first input layer to allow for the whole previous hidden layer in the second and third pass =)
for that it probably helps to blank the first pass recon negative gradient for the empty hidden layer input (cancels the negative bias on hidden1->hidden2 // hidden2->hidden3 weights)

Name: Anonymous 2014-06-06 3:03

>>10
Computer vision tends to use a lot more hand-crafted lower layers (hog, sift, rift, ..) because pixels are spatially correlated, and it would be difficult to learn those custom feature detectors automatically?
You can still just drop the raw pixels into a supervised network, or unsupervised layer (like with an rbm)

Name: Anonymous 2014-06-06 3:03

you will never read SICP for the first time, ever again

Name: Anonymous 2014-06-06 3:41

>>12

Computer vision tends to use a lot more hand-crafted lower layers (hog, sift, rift, ..) because pixels are spatially correlated, and it would be difficult to learn those custom feature detectors automatically?
Anyway, is there a way to infer them automatically? Perhaps using some genetic algorithm? Because programmer doesn't knows what is important and can easily miss some cues, which could have made upper layers order of magnitude more robust.

Name: Anonymous 2014-06-06 4:34

>>14
you can use a convolutional layer, which is sort of the midway point between hand-crafted feature detectors and raw inputs.

Name: Anonymous 2014-06-06 7:10

>>15

It makes sense to automatically select all features, that are invariant under a function (like linear transformations). In general, we can start from sampling random inputs and them throwing away the non-orthogonal combinations.

Name: Anonymous 2014-06-06 9:26

>>16
you can probably get para-orthogonal eigenvectors using pairs of centroids which pivot on & are equidistant to the origin =D

Name: Anonymous 2014-06-06 9:35

Also, if you have a 10x10 px image, doesn't orthogonality limit you to 100 features max?

Name: Anonymous 2014-06-06 12:09

>>5
Read SICP.

Name: Anonymous 2014-06-06 13:59

Wait, what happened to >>2? What was in >>2?

Name: Anonymous 2014-06-06 15:36

>>20
Stop with these posts, you faggot. It was spam (or spam like).

Name: Anonymous 2014-06-06 16:18

>>21
I made only 2 posts like that, you fucking kike. I will question every deleted post

Name: Anonymous 2014-06-06 16:18

DRINK COKE FOR THAT REFRESHING BROWNESS

Name: Anonymous 2014-06-06 17:30

>>22
Calm your shit, faggot. It was actual spam from the guy who made https://progrider.org/prog/read/1402012257 .

Name: Anonymous 2014-06-07 9:13

>>20
admin kike

Name: Anonymous 2014-06-07 9:20

smoke weed everyday

Name: Unreliable storage 2014-06-07 10:25

Unreliable storage

Name: Anonymous 2014-06-08 16:03

-INSANE-PRIEST--INSANE-PRIEST--INSAN
I___________,.-------.,____________I SICP
N______,;~'_____________'~;,_______N fucking
S____,;_____SICP FUCKING____;,_____S sucks
A___;___SUCKS, YOU FUCKING____;____A
N__,'______/PROG/ RETARDS.____',___N Sussman
E_,;___GET IT INTO YOUR HEAD___;,__E is a
-_;_;______._____l_____.______;_;__- cocksucker
P_l_;____________l____________;_l__P
R_l__`/~"_____~"_._"~_____"~\'__l__R SICP
I_l__~__,-~~~^~,_l_,~^~~~-,__~__l__I fucking
E__l___l________}:{__ (O) _l___l___E sucks
S__l___l_ (o) _/_l_\_______!___l___S
T__.~__(__,.--"_.^._"--.,__)__~.___T Sussman
-__l_____---;'_/_l_\_`;---_____l___- is a
-___\__._______V.^.V___((oo))./____- cocksucker
I__O_VI_\________________ll_IV___O_I
N_____I_lT~\___!___!___/~ll_I______N SICP
S_____I_l`IIII_I_I_I_IIIIll_I__o___S fucking
A_O___I__\,III_I_I_I_III,ll_I______A sucks
N______\___`----------'__ll/____o__N
E____O___\___._______.___ll________E Sussman
-_________\..___^____../(_l___O____- is a
P_________/_^___^___^_/__ll\_______P cocksucker
R_O______/`'-l l_l l-';__ll_l___O__R
I_______;_`'=l l_l l='__/ll_l______I
E_____O_l___\l l~l l__l/_ll_l______E Your mother
S_______l\___\ l_l l__;__ll_l__O___S was good
T__o____l_\___ll=l l==\__ll_l______T in bed, she
-____o__l_/\_/\l_l l__l`-ll_/______- grunts like
-_______'-l_`;'l_l l__l__ll_____O__- an ape.
I_O_______l__l l_l l__l__ll________I
N____O____l__l+l_l+l__l__ll___O____N Sussman
S_________l__"""_"""__l__ll________S is a
A__O______l____o_o____l__ll____O___A cocksucker
N_________l,;,;,;,;,;,l__ll________N
E_____O___`lIlIlIlIlIl`__ll________E Original
-__________llIlIlIlIll___ll_____O__- By Dessimat0r
P__________`"""""""""`___""________P (c)2003 Trollkore
-INSANE-PRIEST--INSANE-PRIEST--INSAN

Name: Anonymous 2014-06-08 16:21

>>24
That doesn't seem to be spam

Name: Anonymous 2014-06-08 16:25

>>28
Who's INSANE-PRIEST? I want to bear his children.

Name: Anonymous 2014-06-08 18:46

>>30
You can have my semen.

Don't change these.
Name: Email:
Entire Thread Thread List