神经网络 – 序列预测LSTM神经网络落后

栏目: 数据库 · 发布时间: 5年前

内容简介:翻译自:https://stackoverflow.com/questions/42749541/sequence-prediction-lstm-neural-network-is-falling-behind

我正在尝试实现猜测游戏,其中用户猜测硬币翻转和神经网络试图预测他的猜测(当然没有后见之明的知识).游戏应该是实时的,它适应用户.我使用了突触js,因为它看起来很稳固.

然而,我似乎无法通过一个绊脚石:神经网络不断跟踪它的猜测.就像,如果用户按下

heads heads tail heads heads tail heads heads tail

它确实识别出这种模式,但它却落后于两个动作

tail heads heads tail heads heads tail heads heads

我尝试了无数的策略:

>随着用户与用户一起点击头部或尾部,训练网络

>记录用户条目并清除网络内存,并使用所有条目进行重新训练,直到猜测为止

>通过一系列方式混合搭配训练与激活

>尝试移动到感知器立即传递一堆动作(比LSTM更糟糕)

>一堆我忘记的其他事情

建筑:

> 2个输入,无论用户是否在前一回合中点击了头部或尾部

> 2个输出,预测用户下次点击的内容(这将在下一轮输入)

我已经在隐藏层和各种训练时期尝试了10-30个神经元,但我经常遇到同样的问题!

我将发布我正在执行此操作的bucklescript代码.

我究竟做错了什么?或者我的期望仅仅是无法预测用户猜测实时?有没有替代算法?

class type _nnet = object
    method activate : float array -> float array
    method propagate : float -> float array -> unit
    method clone : unit -> _nnet Js.t
    method clear : unit -> unit
end [@bs]

type nnet = _nnet Js.t

external ltsm : int -> int -> int -> nnet = "synaptic.Architect.LSTM" [@@bs.new]
external ltsm_2 : int -> int -> int -> int -> nnet = "synaptic.Architect.LSTM" [@@bs.new]
external ltsm_3 : int -> int -> int -> int -> int -> nnet = "synaptic.Architect.LSTM" [@@bs.new]
external perceptron : int -> int -> int -> nnet = "synaptic.Architect.Perceptron" [@@bs.new]

type id
type dom
  (** Abstract type for id object *)

external dom : dom = "document" [@@bs.val]

external get_by_id : dom -> string -> id =
  "getElementById" [@@bs.send]

external set_text : id -> string -> unit =
  "innerHTML" [@@bs.set]

(*THE CODE*)

let current_net = ltsm 2 16 2
let training_momentum = 0.1
let training_epochs = 20
let training_memory = 16

let rec train_sequence_rec n the_array =
    if n > 0 then (
        current_net##propagate training_momentum the_array;
        train_sequence_rec (n - 1) the_array
    )

let print_arr prefix the_arr =
    print_endline (prefix ^ " " ^
        (Pervasives.string_of_float (Array.get the_arr 0)) ^ " " ^
        (Pervasives.string_of_float (Array.get the_arr 1)))

let blank_arr =
    fun () ->
    let res = Array.make_float 2 in
    Array.fill res 0 2 0.0;
    res

let derive_guess_from_array the_arr =
    Array.get the_arr 0 < Array.get the_arr 1

let set_array_inp the_value the_arr =
    if the_value then
        Array.set the_arr 1 1.0
    else
        Array.set the_arr 0 1.0

let output_array the_value =
    let farr = blank_arr () in
    set_array_inp the_value farr;
    farr

let by_id the_id = get_by_id (dom) the_id

let update_prediction_in_ui the_value =
    let elem = by_id "status-text" in
    if not the_value then
        set_text elem "Predicted Heads"
    else
        set_text elem "Predicted Tails"

let inc_ref the_ref = the_ref := !the_ref + 1

let total_guesses_count = ref 0
let steve_won_count = ref 0

let sequence = Array.make training_memory false
let seq_ptr = ref 0
let seq_count = ref 0

let push_seq the_value =
    Array.set sequence (!seq_ptr mod training_memory) the_value;
    inc_ref seq_ptr;
    if !seq_count < training_memory then
        inc_ref seq_count

let seq_start_offset () =
    (!seq_ptr - !seq_count) mod training_memory

let traverse_seq the_fun =
    let incr = ref 0 in
    let begin_at = seq_start_offset () in
    let next_i () = (begin_at + !incr) mod training_memory in
    let rec loop () =
        if !incr < !seq_count then (
            let cval = Array.get sequence (next_i ()) in
            the_fun cval;
            inc_ref incr;
            loop ()
        ) in
    loop ()

let first_in_sequence () =
    Array.get sequence (seq_start_offset ())

let last_in_sequence_n n =
    let curr = ((!seq_ptr - n) mod training_memory) - 1 in
    if curr >= 0 then
        Array.get sequence curr
    else
        false

let last_in_sequence () = last_in_sequence_n 0

let perceptron_input last_n_fields =
    let tot_fields = (3 * last_n_fields) in
    let out_arr = Array.make_float tot_fields in
    Array.fill out_arr 0 tot_fields 0.0;
    let rec loop count =
        if count < last_n_fields then (
            if count >= !seq_count then (
                Array.set out_arr (3 * count) 1.0;
            ) else (
                let curr = last_in_sequence_n count in
                let the_slot = if curr then 1 else 0 in
                Array.set out_arr (3 * count + 1 + the_slot) 1.0
            );
            loop (count + 1)
        ) in
    loop 0;
    out_arr

let steve_won () = inc_ref steve_won_count

let propogate_n_times the_output =
    let rec loop cnt =
        if cnt < training_epochs then (
            current_net##propagate training_momentum the_output;
            loop (cnt + 1)
        ) in
    loop 0

let print_prediction prev exp pred =
    print_endline ("Current training, previous: " ^ (Pervasives.string_of_bool prev) ^
        ", expected: " ^ (Pervasives.string_of_bool exp)
        ^ ", predicted: " ^ (Pervasives.string_of_bool pred))

let train_from_sequence () =
    current_net##clear ();
    let previous = ref (first_in_sequence ()) in
    let count = ref 0 in
    print_endline "NEW TRAINING BATCH";
    traverse_seq (fun i ->
        let inp_arr = output_array !previous in
        let out_arr = output_array i in
        let act_res = current_net##activate inp_arr in
        print_prediction !previous i (derive_guess_from_array act_res);
        propogate_n_times out_arr;
        previous := i;
        inc_ref count
    )

let update_counts_in_ui () =
    let tot = by_id "total-count" in
    let won = by_id "steve-won-count" in
    set_text tot (Pervasives.string_of_int !total_guesses_count);
    set_text won (Pervasives.string_of_int !steve_won_count)

let train_sequence (the_value : bool) =
    train_from_sequence ();
    let last_guess = (last_in_sequence ()) in
    let before_train = current_net##activate (output_array last_guess) in
    let act_result = derive_guess_from_array before_train in
    (*side effects*)

    push_seq the_value;

    inc_ref total_guesses_count;
    if the_value = act_result then steve_won ();
    print_endline "CURRENT";
    print_prediction last_guess the_value act_result;
    update_prediction_in_ui act_result;
    update_counts_in_ui ()

let guess (user_guess : bool) =
    train_sequence user_guess

let () = ()

在每次训练迭代之前清除网络上下文是修复

您的代码中的问题是您的网络已经过循环培训.而不是训练1> 2> 3 RESET 1> 2> 3你正在训练网络1> 2> 3> 1> 2> 3.这使您的网络认为3之后的值应为1.

其次,没有理由使用2个输出神经元.有一个就足够了,输出1等于头,输出0等于尾.我们只是围绕输出.

我没有使用Synaptic,而是在此代码中使用了 Neataptic – 它是Synaptic的改进版本,增加了功能和遗传算法.

代码

代码很简单.稍微贬低它,它看起来像这样:

var network = new neataptic.Architect.LSTM(1,12,1);;
var previous = null;
var trainingData = [];

// side is 1 for heads and 0 for tails
function onSideClick(side){
  if(previous != null){
    trainingData.push({ input: [previous], output: [side] });

    // Train the data
    network.train(trainingData, {
      log: 500,
      iterations: 5000,
      error: 0.03,
      clear: true,
      rate: 0.05,
    });

    // Iterate over previous sets to get into the 'flow'
    for(var i in trainingData){
      var input = trainingData[i].input;
      var output = Math.round(network.activate([input]));
    }

    // Activate network with previous output, aka make a prediction
    var input = output;
    var output = Math.round(network.activate([input]))
  }

  previous = side;
}

Run the code here!

这段代码的关键是明确的:是的.这基本上确保网络知道它从第一个训练样本开始,而不是从最后一个训练样本继续. LSTM的大小,迭代次数和学习率是完全可定制的.

成功!

请注意,它需要大约2倍的网络模式才能学习它.

神经网络 – 序列预测LSTM神经网络落后

神经网络 – 序列预测LSTM神经网络落后

神经网络 – 序列预测LSTM神经网络落后

但它确实存在非重复模式的问题:

神经网络 – 序列预测LSTM神经网络落后

翻译自:https://stackoverflow.com/questions/42749541/sequence-prediction-lstm-neural-network-is-falling-behind


以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持 码农网

查看所有标签

猜你喜欢:

本站部分资源来源于网络,本站转载出于传递更多信息之目的,版权归原作者或者来源机构所有,如转载稿涉及版权问题,请联系我们

算法神探

算法神探

[美] 杰瑞米·库比卡 / 啊哈磊、李嘉浩 / 电子工业出版社 / 2017-2 / 65

《算法神探:一部谷歌首席工程师写的CS小说》围绕程序设计典型算法,精心编织了一个扣人心弦又趣味横生的侦探缉凶故事。小说主人公运用高超的搜索技巧和精深的算法知识,最终识破阴谋、缉拿元凶。其间,用二分搜索搜查走私船、用搜索树跟踪间谍、用深度优先搜索逃离监狱、用优先队列开锁及用最佳优先搜索追寻线索等跌宕起伏又富含算法精要的情节,让读者在愉悦的沉浸式体验中快速提升境界,加深对程序世界的理解。《算法神探:一......一起来看看 《算法神探》 这本书的介绍吧!

HEX CMYK 转换工具
HEX CMYK 转换工具

HEX CMYK 互转工具

HSV CMYK 转换工具
HSV CMYK 转换工具

HSV CMYK互换工具