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。
- 技术的马尔可夫链蒙特卡罗Markov chain Monte Carlo (MCMC) uses dependent draws from a carefully designed Markov chain to approximate expectations under a target distribution, often…4 最小阅读量阅读
- 技术的多重比较校正Testing many hypotheses increases the chance of obtaining at least one false positive, even when each test uses the same nominal significance level.3 最小阅读量阅读
- 技术的ARIMA 模型ARIMA models forecast a time series using autoregressive terms, differencing and moving-average terms, summarized by orders p, d and q.3 最小阅读量阅读
- 技术的自相关、ACF 和 PACFAutocorrelation measures linear association between a time series and lagged versions of itself, and the ACF displays it across lags.3 最小阅读量阅读
- 技术的变化点检测Change point detection identifies times when a series' statistical behavior shifts, such as a change in mean, variance or trend.3 最小阅读量阅读
- 技术的DBSCAN 聚类DBSCAN forms clusters from dense neighborhoods and labels points that cannot connect to a sufficiently dense region as noise.3 最小阅读量阅读
- 技术的Dice 系数和分割指标The Dice coefficient measures overlap between predicted and reference regions, balancing false positives and false negatives in one score.3 最小阅读量阅读
- 技术的Exponential Smoothing and Holt-WintersExponential smoothing forecasts a series by updating its level with a weighted combination of recent observations and prior estimates, giving newer…3 最小阅读量阅读
- 技术的用于本地转录的 Faster-Whisper 和 Whisper.cppFaster-Whisper and whisper.cpp are community runtimes for running Whisper speech-recognition models with different implementation and deployment tradeoffs.3 最小阅读量阅读
- 技术的预测精度指标：MAPE、sMAPE 和 MASEForecast metrics summarize how predictions differ from observed values, but MAPE, sMAPE and MASE handle scale and zero values differently.3 最小阅读量阅读
- 技术的高斯混合模型A Gaussian mixture model (GMM) represents a data distribution as a weighted combination of Gaussian components and assigns each observation probabilities…3 最小阅读量阅读
- 技术的层次聚类Hierarchical clustering builds a nested sequence of groups, commonly by repeatedly merging the closest clusters in an agglomerative procedure.3 最小阅读量阅读