chapter 3. We have an additional function build_hp_model() here which takes a hp parameter that refers to a keras_tuner. HyperParameters() object. The hp parameter is used to create hyperparameters which hyperparameters: learning_rate in range [.0001, .01] and dropout_rate in range [.1, .8]. The build_hp_model() is called by the tuner to create a model for each trial with the chosen values for the learning_rate 0002 NUM_CLASSES = 102 def build_hp_model(hp): if hp: learning_rate = hp.Float( "learning_rate", min_value=1e-4, max_value=1e-2, sampling="log" ) dropout_rate = hp.Float( "dropout_rate", min_value=

users, see NVIDIA ® GPU Cloud ™ (NGC) container registry installation documentation based on your platform. ‣ Ensure that you have access and can log in to the NGC container registry. Refer to NGC Getting C++ APIs. ‣ Starting with the 22.05 release, the PyTorch container is available for the Arm SBSA platform. ‣ Deep learning framework containers 19.11 and later include experimental support for Singularity C++ APIs. ‣ Starting with the 22.05 release, the PyTorch container is available for the Arm SBSA platform. ‣ Deep learning framework containers 19.11 and later include experimental support for Singularity

多个环节 • 多种模型 ✗ 海量参数 ✗ 海量数据 从FM到DeepFM rt 增 加了10倍怎么优化？ 2.模型效果优 化困难 1.方案复杂 Data Model Compute Platform 要求:  准确: 低噪声  全面: 同分布 模型选型:  容量大  计算量小 训练推理:  高qps, 低rt  支持超大模型  性价比 流程长、环节多:  推荐场景: 测、语音识别 • 数据集管理 • 主动学习 • 智能标注 itags AI SaaS服务（OCR、语音识别、推荐系统、金融风控、疾病预测等） Infrastructure PAI平台（Platform of Artificial Intelligence） • 一键部署、弹性扩缩 • 多框架、多语言 • 推理优化Blade • 多维度监控+报警 • 自定义镜像 • 全托管+半托管 可视化建模(Designer) 分布式训练(DLC) 在线服务(EAS) 生态市场 开发者工具 • CLI • PAIFlow • OpenAPI AI能力 体验中心 开源 PAI平台（Platform of Artificial Intelligence） Deep Learning Container 数据量大而全 先进的模型结构 业务场景复杂 计算力强、性价比高 提供 支撑

TensorFlow ���������� Baylor, Denis, et al. "Tfx: A tensorflow-based production-scale machine learning platform." Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining TensorFlow ���������� Baylor, Denis, et al. "Tfx: A tensorflow-based production-scale machine learning platform." Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SkyPilot master branch automatically cloned by running: # NOTE: '--platform linux/amd64' is needed for Apple silicon Macs docker run --platform linux/amd64 \ -td --rm --name sky \ -v "$HOME/.sky:/root/.sky:rw"

323 samples, validate on 81 samples Epoch 1/500 2019-09-24 01:07:03.889046: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not co will output the below information: Epoch 1/15 2019-09-24 01:19:01.151247: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not co

“Hello TensorFlow” “Hello TensorFlow” Output: 2018-12-19 02:00:58.943154: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled

be considered as NumPy extension to GPUs. • Computational graphs − PyTorch provides an excellent platform which offers dynamic computational graphs. Thus a user can change them during runtime. • It includes

What is Bloomberg? The Bloomberg Terminal delivers a diverse array of information on a single platform to facilitate financial decision- making. 4 © 2018 Bloomberg Finance L.P. All rights reserved

DeepFM相比于FM模型，相关指标提升4+% • Wide&Deep相比于LR模型，相关指标提升5+% • 效果提升主要来源于Deep部分高阶特征组合 • 但同时对模型服务的性能要求更高 4 深度学习-效果 平台篇 PLATFORM 平台背景、平台架构和平台效果 12 • 平台背景-平台化 成本 效率 效果 实时 机器 人力 时间 开发 运行 迭代 规模 深度 1 平台背景 算法/模型 计算