Recent experiments by Springer and Kenyon have shown that a deep neural network can be trained to predict the action of $t$ steps of Conway's Game of Life automaton given millions of examples of this action on random initial states. However, training was never completely successful for $t>1$, and even when successful, a reconstruction of the elementary rule ($t=1$) from $t>1$ data is not within the scope of what the neural network can deliver. We describe an alternative network-like method, based on constraint projections, where this is possible. From a single data item this method perfectly reconstructs not just the automaton rule but also the states in the time steps it did not see. For a unique reconstruction, the size of the initial state need only be large enough that it and the $t-1$ states it evolves into contain all possible automaton input patterns. We demonstrate the method on 1D binary cellular automata that take inputs from $n$ adjacent cells. The unknown rules in our experiments are not restricted to simple rules derived from a few linear functions on the inputs (as in Game of Life), but include all $2^{2^n}$ possible rules on $n$ inputs. Our results extend to $n=6$, for which exhaustive rule-search is not feasible. By relaxing translational symmetry in space and also time, our method is attractive as a platform for the learning of binary data, since the discreteness of the variables does not pose the same challenge it does for gradient-based methods.
翻译:Springer和Kenyon最近进行的实验表明,如果有可能的话,可以对一个深度神经网络进行培训,以预测Conway的“生命游戏”的“生命自动图案”中“$t $ $” 步骤的动作。但是,如果在随机初始状态上有数以百万计的例子,培训从未完全成功($t>1美元),即使成功,从$t>1美元数据重建基本规则(t=1美元)也不在神经网络所能提供的数据范围内。我们描述了一种基于约束预测的类似网络的替代方法。从一个单一的数据项目中,这一方法完美地重建了“康威”的“生命游戏”规则的“Outomaton automaton automaty”, 不仅在它所看不到的时间步骤中重建了“自动图”规则,而且国家最初状态的规模也不够大,只要它能从它和美元输入模式中演变成包含所有可能的“自动图”输入模式。我们实验中的“1D binary细胞自动图” 的方法并不局限于从“Oral rodeal rudeal ” rode rode rude commoto rode rode rodustration the real redududududududududuductions the s thes s