Added meanAbsoluteError function

Sources/TensorFlow/Loss.swift

@@ -24,6 +24,18 @@ public func meanSquaredError<Scalar: TensorFlowFloatingPoint>(
     return (expected - predicted).squared().mean()
 }
 
+/// Computes the mean absolute error between predictions and expectations.
+///
+/// - Parameters:
+///   - predicted: Predicted outputs from a neural network.
+///   - expected: Expected values, i.e. targets, that correspond to the correct output.
+@differentiable(wrt: predicted)
+public func meanAbsoluteError<Scalar: TensorFlowFloatingPoint>(
+    predicted: Tensor<Scalar>, expected: Tensor<Scalar>
+) -> Tensor<Scalar> {
+    return abs(expected - predicted).mean()
+}
+
 /// Computes the softmax cross entropy (categorical cross entropy) between logits and labels.
 ///
 /// - Parameters:

Tests/TensorFlowTests/LossTests.swift

@@ -27,6 +27,17 @@ final class LossTests: XCTestCase {
         assertElementsEqual(expected: Tensor(expectedLoss), actual: loss)
     }
 
+    func testMeanAbsoluteError() {
+        let predicted = Tensor<Float>(shape: [2, 4], scalars: [1, 2, 3, 4, 5, 6, 7, 8])
+        let expected = Tensor<Float>(
+            shape: [2, 4],
+            scalars: [0.1, 0.2, 0.3, 0.4, 0.4, 0.3, 0.2, 0.1])
+
+        let loss = meanAbsoluteError(predicted: predicted, expected: expected)
+        let expectedLoss: Float = 4.25
+        assertElementsEqual(expected: Tensor(expectedLoss), actual: loss)
+    }
+
     func testMeanSquaredErrorGrad() {
         let predicted = Tensor<Float>(shape: [2, 4], scalars: [1, 2, 3, 4, 5, 6, 7, 8])
         let expected = Tensor<Float>(