update milestone

milestone.md

@@ -4,6 +4,7 @@
 1. [Were RNNs All We Needed?](https://arxiv.org/abs/2410.01201)
 2. [Coding a Recurrent Neural Network (RNN) from scratch using Pytorch](https://solardevs.com/blog/rnn-from-scratch-pytorch/)
 3. [PyTorch RNN Class Documentation](https://pytorch.org/docs/stable/generated/torch.nn.RNN.html)
+4. [MAPE](https://en.wikipedia.org/wiki/Mean_absolute_percentage_error)
 ## Brief Assignment Summary
 Project focuses on predicting parameters of sinusoidal waves using neural networks with minGRU architecture. The core task is to predict amplitude (A) and frequency (ω) parameters from discretized sine wave samples. The waves are defined as y(t) = A sin(ωt) where t ∈ [0, 2π], sampled at 100 points.