深度学习
（张建国）CS3242024秋 2024春 2023春 2021春 2020春2024秋 2024春 2023春 2021春 2020春
9.0(2人评价)
- 课程难度
- 作业多少
- 给分好坏
- 收获大小
| 选课类别：专业任务 | 教学语言：英文 |
| 课程类别：专业选修课 | 开课单位：计算机科学与工程系 |
| 课程层次：未知 | 获得学分：3.0 |
课程主页：暂无（如果你知道，请点右上角“编辑课程信息”添加！）
课程简介（教工部数据）
This course provides an introduction to the field of deep learning, covering the main deep learning techniques from both a theoretical and practical point of view. Architectures that will be covered include Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Autoencoders, and Generative Adversarial Networks (GANs) The goal of the course is that of equipping students with the necessary skills to access the rapidly evolving field of deep learning. To this end lectures and labs will draw multiple links to both the Industry and state-of-the-art academic research, allowing the students to pursue a successful career in both directions. The practical elements of the course will be based on the PyTorch framework, a widely used open source Python framework for deep learning.
This course provides an introduction to the field of deep learning, covering the main deep learning techniques from both a theoretical and practical point of view. Architectures that will be covered include Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Autoencoders, and Generative Adversarial Networks (GANs) The goal of the course is that of equipping students with the necessary skills to access the rapidly evolving field of deep learning. To this end lectures and labs will draw multiple links to both the Industry and state-of-the-art academic research, allowing the students to pursue a successful career in both directions. The practical elements of the course will be based on the PyTorch framework, a widely used open source Python framework for deep learning.
点评写点评
排序学期
评分评分2条点评
评分评分2条点评
- 难度：中等
- 作业：中等
- 给分：超好
- 收获：很多
（同我导的课）
课程讲的东西相对还是比较少的，MLP、反向传播、CNN、RNN/LSTM、AE/VAE、GAN还有最后一节课讲了一点的GCN。平时就只有三次assignment，在一个给定的模版上实现一下课上讲的某些东西，既有手搓也有调包，总体难度不大，但是没有算力的话会很慢（课程会赠送华为☁️的算力）。期末的project是在jetson nano开发板上部署项目，总体来讲还是坑爹的，毕竟硬件…总是会有莫名其妙的问题。期末单选多选计算简答，堪称计算机中的文综，而且必须要用英语答题，不好好复习的同学有福了（不过助教海底捞爽的）。张老师上课很有激情讲的也还比较细，纯英文上课，英文有点口音但还算清楚；实验课王维语老师更是yyds，实验课也没有啥要干的活。总体来讲感觉很不戳的课
- 难度：中等
- 作业：很少
- 给分：一般
- 收获：一般
我导的课，要求感觉挺严格的，project虽然看起来划水，如果不好好做还是会被扣的比较惨的。
作业45%，大部分同学都被扣分了，project 15%也基本拿不了满分。
然后期末考试占40%，平均分75-80分，所以这门课极少部分同学能拿到A和A+
上课的内容的话，还是讲理论比较多，想要玩fancy的deeplearning模型的话，可能要选别的课。
