MTG Salvation

What DSF said. Sentinel should not be passed, not because you should 'hatedraft' it, but because anyone can splash it with a little effort.

I'm curious as to the extent people think that the seeded pack has distorted the view of the environment.

Inferm: Could you explain your comment a bit more? You say 'it did some work against [you]', but also that you 'never lost against it'. These two statements seem to be at odd with each other.

If Tutelage never won a game against you, I have difficulty understanding how it 'did some work'.

I like Sendai's suggestion quite a lot. Removing a systematic syntax removes the bias associated with that syntax. I do believe, though, that this implies that the NN would need more time to learn how to use mana costs at all, as it has to learn that 11R, 1R1, and R11 are all equivalent in addition to everything else.

Talcos: Something I noted was that you posted a red card that had, in effect, Lightning Helix on it. I was wondering... what happens to a network trained solely on monocolor cards, which is then given priming for a multicolor card? I am quite interested in knowing whether it creates a menu-based card (like Lightning Helix) or something more blended.

The reason I ask is because the above makes me think that the network 'learned' that Lightning Helix is a 'red' effect, when it is actually a 'white/red' effect. Given the realities of Magic design, this might point to the need for a tighter encoding of mana costs. E.g., you may need to code RB as a single character, rather than two separate mana symbols. This would allow the network to more easily learn that certain effects belong to interactions of colors rather than just one. I am afraid of the lack of learning it might make overall, but Lightning Helix's text should never appear on a monored card.

I dunno... The issue is one of space, I guess.

Talcos: I'm homing in on a skeleton. Do we want to try to give it new keywords, or make a core-like set?

Mustard: Well, from a philosophical perspective, you might want to ask why it is that humans do have consciousness to the degree that we can design things such as, e.g., the forum we're using, and yet no other lifeform, to our knowledge, can do this.

It can't be a question of just the sophistication of our brains, though that certainly assists. Even with my limited knowledge of NNs, I can get the 'equivalent' of very robust 'thinking' out of a NN that is very simple.

What I think is missing, really, is the self-spurring nature of things. It is fairly straightforward to use a NN to do what we have done, here. But a NN doesn't 'learn' in the sense that we do. There is no consciousness internal to the NN directing it.

Let us use your example of language acquisition. Assuming that most people primarily use words to think with, the question is not how did you learn so much as why. My own anecdotal evidence (from having a large extended family and thus many nieces and nephews) is that children acquire language to communicate. It is something they want to do, and having made the leap that the sounds they're hearing are a way to communicate. Once they decide to acquire language, then yes, the method of learning can be approximated with a NN-type approach.

Faust: I was just yesterday reading Strunk and White on this very topic, and the construction used is correct.

The only exception given for singular nouns are ancient proper names that end is -es or -is, or Jesus. Quite literally.

Now, if they had decided to use this exception, Erebos would probably slide in fairly well.

Anyone else notice the red creature with Reach? That's... fairly new, isn't it?

Talcos (or anyone else lurking), here's a statistics theory question. Say I have an output source (like a mini neural net that we want to generate new valid training inputs). Its output has a particular distribution that I like. How do I filter the outputs without changing this distribution? Is this even possible?

I have some knowledge of statistics. First question, what is the distribution of?

I'll start looking into it, Talcos. While I have a broad understanding of machine learning and neural networks, I have limited familiarity with the specific networks you're running, so I figure that I can try to help in ancillary ways.

Talcos: If you like, I could come up with a design skeleton for a set for you to try out.

Also, should we not be able to give it a historical design skeleton (say, for Magic 2014) and see how close it can come to reproducing the set?

Talcos: That's awesome!

I like how Delusion only really showed up in UBR (with one White card with a Black outlier). Is this representative, or did you cherrypick?

Now, another question. Can the NN be used for hole-filling? Let's say that you have a set made (with the NN or not), and you have a certain low number of holes in the set. Could you take your NN, feed it your set, and have it hole-fill for you?

Talcos: A very small point that I don't expect the NN to grasp, but every Soratami (Moonfolk) printed with the type (i.e., other than Tamiyo) has an ability that bounces land to your hand. It seems odd that they don't have them now.

Also, could you have the network make cards with the following ability?

Delusion X - When ~ enters the battlefield, gain X life. When ~ leaves the battlefield, lose X life.

Mustard: Bool Slash is Delay from Time Spiral block, with upside.

Just wanted to say that this thread is awesome, and I would like to point out that the above card Dragon's Revelation is a completely reasonable card that could actually be in Origins.

Sword of the Pierced Totem is actually completely feasible as well. Well, except for the minor point that I don't think Spell Mastery shows up on non-Sorcery/Instant spells.

I am really looking forward to a created set of cards with the network.

Talcos, I am correct in believing that this will be able to (at some point) take a design skeleton and mechanics for a set and create the set, correct?

Flavor check: Can these be the Maalfeld twins?

seiloque: I highly doubt that this is in the same cycle as Chandra's Ignition.

But sure, I'll take this Kodama's Reach variant.