从这里开始
从这里开始
五 成果导向课程
每门课程都包含明确的成果、能力规划、实践活动和应用毕业设计。
主题曲目
按曲目浏览
跳入您关心的领域。每条赛道都有多个简单的英文指南。
- 91 指南基础知识核心概念：人工智能如何在高层次上工作。探索
- 177 指南语言人工智能LLM、NLP、ChatGPT、提示和文本理解。探索
- 170 指南视觉人工智能图像生成、计算机视觉、视频和设计。探索
- 124 指南音频人工智能语音、音乐、播客和音频优先的人工智能。探索
- 123 指南公司OpenAI、Anthropic、Google、Meta 等的配置文件。探索
- 346 指南应用领域人工智能如何出现在编码、搜索、代理和日常生活中。探索
- 165 指南行业医疗保健、金融、教育、能源等领域的人工智能。探索
- 319 指南技术的芯片、微调、RAG、向量和人工智能基础设施。探索
- 142 指南社会偏见、隐私、版权、安全和人工智能的未来。探索
全库
所有指南
1657 的 1657 显示指南。按曲目过滤或在上方搜索。
- 技术的学习曲线和验证曲线Learning curves show how training and validation performance changes as the amount of training data or training time changes.3 最小阅读量阅读
- 技术的LIME 本地解释LIME explains one prediction by fitting a simple, interpretable surrogate near the example being examined.3 最小阅读量阅读
- 技术的线性判别分析Linear discriminant analysis is a supervised method that models class distributions to classify observations and can project data into directions…3 最小阅读量阅读
- 技术的部分相关图A partial dependence plot estimates how a model's predictions change as selected feature values vary, averaging over observed values of other features.3 最小阅读量阅读
- 技术的AdaBoostAdaBoost builds an ensemble of weak learners in sequence, increasing attention on training examples that earlier learners classified incorrectly.3 最小阅读量阅读
- 技术的DICOM and Medical Imaging Data FormatsDICOM is a standard for exchanging medical images and related information, with pixel data and structured attributes that describe the study and acquisition.3 最小阅读量阅读
- 技术的广义线性模型A generalized linear model (GLM) relates predictors to an outcome through a linear predictor, a response distribution and a link function.4 最小阅读量阅读
- 技术的铰链损失Hinge loss penalizes a classification example when its signed margin falls below one, including correctly classified points that sit too close…4 最小阅读量阅读
- 应用领域如何使用人工智能选择油漆颜色人工智能和数字油漆可视化工具可以通过预览房间照片上的调色板来帮助缩小颜色选择范围。3 最小阅读量阅读
- 应用领域如何利用人工智能可视化房间重新设计AI room visualizations turn a photo or description into possible decorating concepts, such as a different furniture arrangement or color palette.3 最小阅读量阅读
- 技术的Huber 损失和鲁棒回归Huber loss is quadratic for small residuals and linear for large residuals, reducing the influence of extreme errors compared with squared loss…4 最小阅读量阅读
- 技术的The Kernel TrickThe kernel trick lets an algorithm that depends on inner products behave as if it used a richer feature representation, without explicitly constructing every…3 最小阅读量阅读