广发证券首席金工分析师 安宁宁 SAC: S0260512020003 anningning@gf.com.cn 广发证券资深金工分析师 张钰东 SAC: S0260522070006 zhangyudong@gf.com.cn 广发金工安宁宁陈原文团队 摘要 最近5个交易日，科创50指数跌0.40%，创业板指涨1.74%，大盘价值跌0.30%，大盘成长涨0.89%，上证50跌0.33%，国证2000代表的小盘涨2.38%，汽车、 美容护理市场表现靠前，食品饮料、房地产表现靠后。 风险溢价，中证全指静态PE的倒数EP减去十年期国债收益率，权益与债券资产隐含收益率对比，历史数次极端底部该数据均处在均值上两倍标准差区 域，比如2012/2018/2020年（疫情突发），2022/04/26达到4.17%，2022/10/28风险溢价再次上升到4.08%，市场迅速反弹，2024/01/19指标4.11%，自2016年 以来第五次超过4%。截至2025/04/25指标3.99%，两倍标准差边界为4.75%。 估值水平，截至2025/04/25，中证全指PETTM分位数48%，上证50与沪深300分别为60%、46%， ...

Market Performance - The recent 5 trading days saw the Sci-Tech 50 Index decline by 0.31%, the ChiNext Index by 0.64%, while large-cap value stocks rose by 2.62% and large-cap growth stocks fell by 0.24% [1] - The banking and real estate sectors performed well, while defense, military, agriculture, forestry, animal husbandry, and fishery sectors lagged behind [1] Risk Premium Analysis - The risk premium, measured as the inverse of the static PE of the CSI All Share Index minus the yield of 10-year government bonds, has reached historical extremes, with values exceeding 4% on multiple occasions since 2016 [1] - As of April 18, 2025, the risk premium stood at 4.05%, with the two-standard deviation boundary at 4.74% [1] Valuation Levels - As of April 18, 2025, the CSI All Share Index's TTM PE percentile is at 47%, with the SSE 50 and CSI 300 at 60% and 45% respectively, indicating that the ChiNext Index is relatively undervalued at close to 9% [2] - The long-term view of the Deep 100 Index suggests a cyclical pattern of bear and bull markets every three years, with the current adjustment phase starting in Q1 2021 showing sufficient time and space for a potential upward cycle [2] Fund Flow and Trading Activity - In the last 5 trading days, ETF inflows totaled 24.3 billion yuan, while margin trading decreased by approximately 3.4 billion yuan, with an average daily trading volume of 1,076.1 billion yuan across the two markets [3] AI and Data Analysis - The use of convolutional neural networks to model price and volume data has been explored, with features mapped to industry themes, indicating a focus on sectors such as banking and securities as of April 18, 2025 [2][8]

广发证券首席金工分析师 安宁宁 SAC: S0260512020003 anningning@gf.com.cn 广发证券资深金工分析师 张钰东 SAC: S0260522070006 zhangyudong@gf.com.cn 广发金工安宁宁陈原文团队 摘要 最近5个交易日，科创50指数跌0.31%，创业板指跌0.64%，大盘价值涨2.62%，大盘成长跌0.24%，上证50涨1.45%，国证2000代表的小盘涨0.05%，银行、 房地产市场表现靠前，国防军工、农林牧渔表现靠后。 风险溢价，中证全指静态PE的倒数EP减去十年期国债收益率，权益与债券资产隐含收益率对比，历史数次极端底部该数据均处在均值上两倍标准差区 域，比如2012/2018/2020年（疫情突发），2022/04/26达到4.17%，2022/10/28风险溢价再次上升到4.08%，市场迅速反弹，2024/01/19指标4.11%，自2016年 以来第五次超过4%。截至2025/04/18指标4.05%，两倍标准差边界为4.74%。 估值水平，截至2025/04/18，中证全指PETTM分位数47%，上证50与沪深300分别为60%、45%， ...

广发证券首席金工分析师 安宁宁 SAC: S0260512020003 anningning@gf.com.cn 广发证券资深金工分析师 张钰东 SAC: S0260522070006 广发金工安宁宁陈原文团队 摘要 最近5个交易日，科创50指数跌0.63%，创业板指跌6.73%，大盘价值跌2.61%，大盘成长跌3.37%，上证50跌1.60%，国证2000代表的小盘跌6.29%，农林牧 渔、商贸零售市场表现靠前，电力设备、通信表现靠后。 风险溢价，中证全指静态PE的倒数EP减去十年期国债收益率，权益与债券资产隐含收益率对比，历史数次极端底部该数据均处在均值上两倍标准差区 域，比如2012/2018/2020年（疫情突发），2022/04/26达到4.17%，2022/10/28风险溢价再次上升到4.08%，市场迅速反弹，2024/01/19指标4.11%，自2016年 以来第五次超过4%。截至2025/04/11指标4.09%，两倍标准差边界为4.73%。 估值水平，截至2025/04/11，中证全指PETTM分位数45%，上证50与沪深300分别为56%、43%，创业板指接近9%，中证500与中证1000 ...

Market Performance - The recent five trading days saw the Sci-Tech 50 Index decline by 0.63%, the ChiNext Index drop by 6.73%, and the large-cap value index decrease by 2.61% [1] - The agricultural, forestry, animal husbandry, and fishery sectors, along with retail trade, performed well, while the power equipment and telecommunications sectors lagged behind [1] Risk Premium Analysis - The risk premium, measured as the inverse of the static PE of the CSI All Share Index minus the yield of ten-year government bonds, indicates that the implied returns of equity and bond assets are at historically high levels, reaching 4.17% on April 26, 2022, and 4.11% on January 19, 2024 [1] - As of April 11, 2025, the risk premium stands at 4.09%, with the two-standard deviation boundary at 4.73% [1] Valuation Levels - As of April 11, 2025, the CSI All Share Index's PE TTM percentile is at 45%, with the SSE 50 and CSI 300 at 56% and 43% respectively, indicating that the ChiNext Index is at a relatively low valuation compared to historical levels [2] - The long-term view of the Deep 100 Index suggests a cyclical pattern of bear and bull markets every three years, with the current adjustment phase starting in Q1 2021 showing sufficient time and space for a potential upward cycle [2] Fund Flow and Trading Activity - In the last five trading days, ETF inflows totaled 206.9 billion yuan, while margin financing decreased by approximately 98.3 billion yuan, with an average daily trading volume of 1.5742 trillion yuan [3] AI and Machine Learning Insights - The use of convolutional neural networks (CNN) for modeling price and volume data has been explored, with features mapped to industry themes, indicating a focus on sectors like securities as of April 11, 2025 [7][2]

Market Performance - The recent 5 trading days saw the Sci-Tech 50 Index decline by 1.29%, and the ChiNext Index drop by 1.12%, while the large-cap value index rose by 0.28% and the large-cap growth index increased by 0.04% [1] - The healthcare and agriculture sectors performed well, whereas the computer and defense industries lagged behind [1] Risk Premium Analysis - The static PE of the CSI All Share Index minus the yield of 10-year government bonds indicates a risk premium, which has historically reached extreme levels at two standard deviations above the mean during significant market bottoms [1] - As of January 19, 2024, the risk premium indicator was at 4.11%, marking the fifth occurrence since 2016 of exceeding 4% [1] Valuation Levels - As of March 28, 2025, the CSI All Share Index's PE TTM percentile was at 53%, with the SSE 50 and CSI 300 at 58% and 48% respectively, while the ChiNext Index was close to 14% [2] - The ChiNext Index's valuation is relatively low compared to historical averages [2] Long-term Market Trends - The Shenzhen 100 Index has experienced bear markets approximately every three years, followed by bull markets, with declines ranging from 40% to 45% [2] - The current adjustment cycle, which began in Q1 2021, appears to have sufficient time and space for a potential upward trend [2] Fund Flow and Trading Activity - In the last 5 trading days, ETF inflows totaled 16.2 billion yuan, while margin financing decreased by approximately 24.8 billion yuan [3] - The average daily trading volume across both markets was 1.2346 trillion yuan [3] Thematic Investment Focus - As of March 28, 2025, the recommended investment themes include construction materials and low-volatility dividend stocks [2][8]

如果您希望可以时常见面，欢迎标星收藏哦~ 来源：内容来自计算机历史博物馆（CHM），谢谢。 计算机历史博物馆（CHM）与Google合作，发布了AlexNet 的源代码。AlexNet 是一个神经网 络，于 2012 年开启了当今流行的 AI 方法。该源代码可在CHM 的 GitHub 页面上以开源形式获 取。 什么是 AlexNet？ AlexNet 是 一 个 人 工 神 经 网 络 ， 用 于 识 别 照 片 内 容 。 它 由 当 时 的 多 伦 多 大 学 研 究 生 Alex Krizhevsky 和 Ilya Sutskever 以及他们的导师 Geoffrey Hinton 于 2012 年开发。 深度学习的起源 杰弗里·辛顿被认为是"深度学习"之父之一。深度学习是一种使用神经网络的人工智能，也是当今 主流人工智能的基础。上世纪 50 年代末，康奈尔大学研究员弗兰克·罗森布拉特首次构建了简单 的三层神经网络，其中只有一层自适应权重，但人们发现这种网络存在局限性。人们需要具有多层 自适应权重的网络，但没有很好的方法来训练它们。到 20 世纪 70 年代初，神经网络已被人工智 能研究人员普遍拒绝。 ...

广发证券首席金工分析师 安宁宁 anningning@gf.com.cn 广发证券资深金工分析师 陈原文 chenyuanwen@gf.com.cn 联系人：广发证券金工研究员 林涛 gflintao@gf.com.cn 广发金工安宁宁陈原文团队 摘要 神经常微分方程： 在机器学习国际顶会NeurIPS 2018上，Chen等人发表的论文《Neural Ordinary Differential Equations》获得了大会的最佳论文奖。简单来 说，一个常见的ResNet网络通常由多个形如h_{t+1}=f(h_t,_t)+h_t的残差结构所组成。在常规求解中，需计算出每一个残差结构中最能拟合训练数据的网 络参数。而该论文提出，假设当ResNet网络中的残差结构无限堆叠时，则每一个残差结构的参数都可以通过求解同一个常微分方程来获得。 液态神经网络： 基于上述工作，来自麻省理工学院的Ramin Hasani等人，创新性地以常微分方程的形式描述循环神经网络的隐藏状态变化，提出了一类被 称之为液态神经网络的模型，这些研究成果被发表在《Nature：Machine Intelligence》等国际顶级期刊上。此类模 ...