Глубокое обучение Intellij Maven4j

Я пытаюсь настроить проект maven в IntelliJ, и мне нужны полные актуальные инструкции о том, как выполнить настройку для deeplearning4j, потому что я продолжаю сталкиваться с такими ошибками, как:

java.lang.NoClassDefFoundError: не удалось инициализировать класс org.nd4j.linalg.factory.Nd4j и java.lang.ExceptionInInitializerError (это когда я использую Kotlin REPL). Я также получаю эти предупреждения, когда запускаю программу в обычном режиме: log4j:WARN Не удалось найти приложения для регистратора (org.nd4j.linalg.factory.Nd4jBackend).

Это мой файл pom.xml:

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>

<groupId>org.example</groupId>
<artifactId>Test</artifactId>
<version>1.0-SNAPSHOT</version>
<packaging>jar</packaging>

<name>org.example Test</name>

<properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <kotlin.version>1.3.61</kotlin.version>
    <kotlin.code.style>official</kotlin.code.style>
    <junit.version>4.12</junit.version>
</properties>

<dependencies>
    <dependency>
        <groupId>org.jetbrains.kotlin</groupId>
        <artifactId>kotlin-stdlib</artifactId>
        <version>${kotlin.version}</version>
    </dependency>
    <dependency>
        <groupId>org.nd4j</groupId>
        <artifactId>nd4j-common</artifactId>
        <version>1.0.0-beta6</version>
    </dependency>
        <dependency>
            <groupId>org.deeplearning4j</groupId>
            <artifactId>deeplearning4j-core</artifactId>
            <version>1.0.0-beta4</version>
        </dependency>
        <dependency>
            <groupId>org.nd4j</groupId>
            <artifactId>nd4j-native-platform</artifactId>
            <version>1.0.0-beta4</version>
        </dependency>
    <dependency>
        <groupId>org.slf4j</groupId>
        <artifactId>slf4j-api</artifactId>
        <version>1.7.5</version>
    </dependency>
    <dependency>
        <groupId>org.slf4j</groupId>
        <artifactId>slf4j-api</artifactId>
        <version>1.7.5</version>
    </dependency>
    <dependency>
        <groupId>org.slf4j</groupId>
        <artifactId>slf4j-api</artifactId>
        <version>1.7.5</version>
    </dependency>
    <dependency>
        <groupId>org.slf4j</groupId>
        <artifactId>slf4j-log4j12</artifactId>
        <version>1.7.5</version>
    </dependency>
    <dependency>
        <groupId>org.nd4j</groupId>
        <artifactId>nd4j-jblas</artifactId>
        <version>0.0.3.5.5.4-SNAPSHOT</version>
    </dependency>
</dependencies>

<build>
    <sourceDirectory>src/main/kotlin</sourceDirectory>
    <testSourceDirectory>src/test/kotlin</testSourceDirectory>

    <plugins>
        <plugin>
            <groupId>org.jetbrains.kotlin</groupId>
            <artifactId>kotlin-maven-plugin</artifactId>
            <version>${kotlin.version}</version>
            <executions>
                <execution>
                    <id>compile</id>
                    <phase>compile</phase>
                    <goals>
                        <goal>compile</goal>
                    </goals>
                </execution>
                <execution>
                    <id>test-compile</id>
                    <phase>test-compile</phase>
                    <goals>
                        <goal>addSources</goal>
                        <goal>test-compile</goal>
                    </goals>
                </execution>
            </executions>
        </plugin>
    </plugins>
</build>

This is my program (taken from nd4j examples):

import org.nd4j.linalg.api.ndarray.INDArray
import org.nd4j.linalg.factory.Nd4j
import java.util.*

class Test3
{

}

fun main() { /*
        Before we begin, let's review what an INDArray is:
        A INDArray is a multi-dimensional array of numbers: a vector, matrix, or tensor for example.
        Internally, it may store single precision or double precision floating point values for each entry.
        Here, we'll see how you can get some basic information about INDArrays. In later examples, we'll see
        the different ways to create INDArrays, and more operations we can do on them.
         */
//Let's start by creating a basic 2d array: a matrix with 3 rows and 5 columns. All elements are 0.0
    val nRows = 3
    val nColumns = 5
    val myArray: INDArray = Nd4j.zeros(nRows, nColumns)
    //Next, print some basic information about the array:
    System.out.println("Basic INDArray information:")
    System.out.println("Num. Rows:          " + myArray.rows())
    System.out.println("Num. Columns:       " + myArray.columns())
    System.out.println("Num. Dimensions:    " + myArray.rank()) //2 dimensions -> rank 2
    System.out.println("Shape:              " + Arrays.toString(myArray.shape())) //[3,5] -> 3 rows, 5 columns
    System.out.println("Length:             " + myArray.length()) // 3 rows * 5 columns = 15 total elements
    //We can print the array itself using toString method:
    System.out.println("\nArray Contents:\n$myArray")
    //There are some other ways we can get the same or similar info
    System.out.println()
    System.out.println("size(0) == nRows:   " + myArray.size(0)) //Also equivalent to: .shape()[0]
    System.out.println("size(1) == nCols:   " + myArray.size(1)) //Also equivalent to: .shape()[1]
    System.out.println("Is a vector:        " + myArray.isVector())
    System.out.println("Is a scalar:        " + myArray.isScalar())
    System.out.println("Is a matrix:        " + myArray.isMatrix())
    System.out.println("Is a square matrix: " + myArray.isSquare())
    //Let's make some modifications to our array...
// Note that indexing starts at 0. Thus 0..2 are valid indices for rows, and 0..4 are valid indices for columns here
    myArray.putScalar(0, 1, 2.0) //Set value at row 0, column 1 to value 2.0
    myArray.putScalar(2, 3, 5.0) //Set value at row 2, column 3 to value 5.0
    System.out.println("\nArray after putScalar operations:")
    System.out.println(myArray)
    //We can also get individual values:
    val val0: Double = myArray.getDouble(0, 1) //Get the value at row 0, column 1 - expect value 2.0 as we set this earlier
    System.out.println("\nValue at (0,1):     $val0")
    //Finally, there are many things we can do to the array... for example adding scalars:
    val myArray2: INDArray = myArray.add(1.0) //Add 1.0 to each entry
    System.out.println("\nNew INDArray, after adding 1.0 to each entry:")
    System.out.println(myArray2)
    val myArray3: INDArray = myArray2.mul(2.0) //Multiply each entry by 2.0
    System.out.println("\nNew INDArray, after multiplying each entry by 2.0:")
    System.out.println(myArray3)
}