- Hands-On Meta Learning with Python
- Sudharsan Ravichandiran
- 110字
- 2021-07-02 14:29:22
Summary
In this chapter, we started off with prototypical networks, and we saw how a prototypical network computes the class prototype using the embedding function and predicts the class label of the query set by comparing the Euclidean distance between the class prototype and query set embeddings. Following this, we experimented with a prototypical network by performing classification on an omniglot dataset. Then, we learned about the Gaussian prototypical network, which, along with the embeddings, also uses the covariance matrix to compute the class prototype. Following this, we explored semi-prototypical networks, which are used to handle semi-supervised classes. In the next chapter, we will learn about relation and matching networks.
推薦閱讀
- PyTorch深度學(xué)習(xí)實(shí)戰(zhàn):從新手小白到數(shù)據(jù)科學(xué)家
- 企業(yè)數(shù)字化創(chuàng)新引擎:企業(yè)級(jí)PaaS平臺(tái)HZERO
- Hands-On Machine Learning with Microsoft Excel 2019
- 數(shù)據(jù)之巔:數(shù)據(jù)的本質(zhì)與未來(lái)
- MongoDB管理與開發(fā)精要
- 分布式數(shù)據(jù)庫(kù)系統(tǒng):大數(shù)據(jù)時(shí)代新型數(shù)據(jù)庫(kù)技術(shù)(第3版)
- 城市計(jì)算
- Hands-On Mathematics for Deep Learning
- Proxmox VE超融合集群實(shí)踐真?zhèn)?/a>
- Hadoop集群與安全
- Augmented Reality using Appcelerator Titanium Starter
- 區(qū)塊鏈技術(shù)應(yīng)用與實(shí)踐案例
- 聯(lián)動(dòng)Oracle:設(shè)計(jì)思想、架構(gòu)實(shí)現(xiàn)與AWR報(bào)告
- 實(shí)現(xiàn)領(lǐng)域驅(qū)動(dòng)設(shè)計(jì)
- 利用Python進(jìn)行數(shù)據(jù)分析(原書第2版)