functionality. PyTorch also includes standard defined neural network layers, deep learning optimizers, data loading utilities, and multi-gpu, and multi-node support. Functions are executed immediately instead nvcr.io/nvidia/ pytorch:-py3 Note: If you use multiprocessing for multi-threaded data loaders, the default shared memory segment size with which the container runs might not be enough To pull data and model descriptions from locations outside the container for use by PyTorch or save results to locations outside the container, mount one or more host directories as Docker® data volumes

Python usage − This library is considered to be Pythonic which smoothly integrates with the Python data science stack. • It can be considered as NumPy extension to GPUs. • Computational graphs − PyTorch Dataloader • Visualization Tools like • TensorboardX (monitor training) • PyTorchViz (visualise computation graph) • Various other functions • loss (MSE,CE etc..) • optimizers Prepare Input Data •Load data requires_grad=True) •Accessing tensor value: • t.data •Accessing tensor gradient • t.grad • grad_fn – history of operations for autograd • t.grad_fn Loading Data, Devices and CUDA • Numpy arrays to PyTorch

recap, learning techniques can help us meet our model quality goals. Techniques like distillation and data augmentation improve the model quality, without increasing the footprint of the model (size, latency As we described in chapter 3’s ‘Learning Techniques and Efficiency’ section, labeling of training data is an expensive undertaking. Factoring in the costs of training human labelers on a given task, and significantly improve the quality you can achieve while retaining the same labeling costs i.e., training data-efficient (specifically, label efficient) models. We will describe the general principles of Self-Supervised

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 233 18 可视化 Visualization 234 19 Scikit-learn API 235 20 工具 236 20.1 CustomObjectScope [source] . . . . . . . . . . metrics=['accuracy']) # 生成虚拟数据 import numpy as np data = np.random.random((1000, 100)) labels = np.random.randint(2, size=(1000, 1)) # 训练模型，以 32 个样本为一个 batch 进行迭代 model.fit(data, labels, epochs=10, batch_size=32) compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy']) # 生成虚拟数据 import numpy as np data = np.random.random((1000, 100)) labels = np.random.randint(10, size=(1000, 1)) # 将标签转换为分类的 one-hot

platform." Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2017. TFX - �� TensorFlow ���������� Baylor, Denis, et al. "Tfx: A tensorflow-based platform." Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2017. TFX - �� TensorFlow ���������� https://github.com/tensorflow/tfx TFX - �� TensorFlow ��-Kubeflow ���� AI ���� Business Requirement Production Design Data Processing Model Training Model Visualization Model Serving Production Verification Business Success ���� �����

https://towardsdatascience.com/supervised-vs-unsupervised-learning-14f68e32ea8d Massive Unlabeled data Unsupervised Learning https://medium.com/intuitionmachine/predictive-learning-is-the-key-to-deep-learning- Preprocessing: Huge dimension, say 224x224, is hard to process ▪ Visualization: https://projector.tensorflow.org/ ▪ Taking advantages of unsupervised data ▪ Compression, denoising, super-resolution … Auto-Encoders PCA V.S. Auto-Encoders ▪ PCA, which finds the directions of maximal variance in high- dimensional data, select only those axes that have the largest variance. ▪ The linearity of PCA, however, places

People’s Posts and Telecommunications Press, 2016 Trevor Hastie, The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd Ed.), World Publishing Corporation, 2015 Christopher M. Bishop Personalized news or mail filter Personalized tutoring Discover new knowledge from large databases (data mining) Market basket analysis (e.g. diapers and beer) Medical information mining (e.g. migraines given only indirect feedback? Feng Li (SDU) Overview September 6, 2023 14 / 57 Source of Training Data Provided random examples outside of the learner’s control. Negative examples available or only positive

Discovering Clusters in Large Spatial Databases with Noise[J]. Proc.int.conf.knowledg Discovery & Data Mining, 1996. [3] Andrew Ng. Machine Learning[EB/OL]. Stanford University,2014. https://www.coursera A, et al. Hierarchical Density Estimates for Data Clustering, Visualization, and Outlier Detection[J]. Acm Transactions on Knowledge Discovery from Data, 2015. [11] 彭 涛 . 人 工 智 能 概 论 [EB/OL]. 北 京 联

Overview of Compression One of the simplest approaches towards efficiency is compression to reduce data size. For the longest time in the history of computing, scientists have worked tirelessly towards popular example of lossless data compression algorithm is Huffman Coding, where we assign unique strings of bits (codes) to the symbols based on their frequency in the data. More frequent symbols are assigned and the path to that symbol is the bit-string assigned to it. This allows us to encode the given data in as few bits as possible, since the most frequent symbols will take the least number of bits to

features in the input. Recurrent Neural Nets (RNNs) facilitated learning from the sequences and temporal data. These breakthroughs contributed to bigger and bigger models. Although they improved the quality of you see, books you read, food you enjoy and so on), without the need of knowing all the encyclopedic data about them. When working with deep learning models and inputs such as text, which are not in numerical high-dimensional data into low-dimension, while retaining the properties from the high-dimensional representation. It is useful because it is often computationally infeasible to work with data that has a large