Deep Learning
深度学习聚焦于多层神经网络模型的理论与实践。课程内容包括前馈神经网络、反向传播算法、卷积神经网络（CNN）、循环神经网络（RNN/LSTM）、Transformer架构、优化算法、正则化技术以及主流框架（PyTorch/TensorFlow）。学生将理解模型设计、训练技巧与表示学习原理，能够应用于图像、语音、自然语言等任务，是AI方向的核心进阶课程。
Deep Learning focuses on the theory and practice of multi-layer neural networks. Topics include feedforward networks, backpropagation, convolutional neural networks (CNNs), recurrent neural networks (RNN/LSTM), Transformers, optimization algorithms, regularization techniques, and mainstream frameworks such as PyTorch and TensorFlow. Students gain skills in model design, training, and representation learning, applicable to vision, speech, and language tasks—a core advanced AI course.
学生需基于CIFAR-10数据集构建图像分类模型。要求使用PyTorch或TensorFlow实现CNN架构（如ResNet），完成数据增强、训练、验证与测试，测试集准确率需达到92%以上。需对比不同架构、优化器与正则化策略的效果，提交代码、训练曲线及分析报告，讨论过拟合处理方法。
Students build an image classification model on the CIFAR-10 dataset using PyTorch or TensorFlow. The project requires implementing a CNN architecture such as ResNet, with data augmentation, training, validation, and testing, achieving over 92% test accuracy. Deliverables include code, training curves, and an analysis report comparing architectures, optimizers, and regularization strategies, discussing overfitting mitigation.