信息加载中,请等待...

主页/IT编程----在更/极客时间视频-在更/30-NLP实战高手课/

网盘目录系统教程
01-课程介绍[防断更微lxknumber1].ts
02-内容综述[防断更微lxknumber1].ts
03-AI概览：宣传片外的人工智能[防断更微lxknumber1].mp4
04-AI项目流程：从实验到落地[防断更微lxknumber1].mp4
05-NLP领域简介：NLP基本任务及研究方向[防断更微lxknumber1].mp4
06-NLP应用：智能问答系统[防断更微lxknumber1].mp4
07-NLP应用：文本校对系统[防断更微lxknumber1].mp4
08-NLP的学习方法：如何在AI爆炸时代快速上手学习？[防断更微lxknumber1].mp4
09-深度学习框架简介：如何选择合适的深度学习框架？[防断更微lxknumber1].mp4
10-深度学习与硬件：CPU[防断更微lxknumber1].mp4
100-WikiSQL任务简介[防断更微lxknumber1].mp4
101-ASDL和AST[防断更微lxknumber1].mp4
102-Tranx简介[防断更微lxknumber1].mp4
103-LambdaCaculus概述[防断更微lxknumber1].mp4
104-Lambda-DCS概述[防断更微lxknumber1].mp4
105-InductiveLogicProgramming：基本设定[防断更微lxknumber1].mp4
106-InductiveLogicProgramming：一个可微的实现[防断更微lxknumber1].mp4
107-增强学习的基本设定：增强学习与传统的预测性建模有什么区别？[防断更微lxknumber1].mp4
108-最短路问题和DijkstraAlgorithm[防断更微lxknumber1].mp4
109-Q-learning：如何进行Q-learning算法的推导？[防断更微lxknumber1].mp4
11-深度学习与硬件：GPU[防断更微lxknumber1].mp4
110-Rainbow：如何改进Q-learning算法？[防断更微lxknumber1].mp4
111-PolicyGradient：如何进行PolicyGradient的基本推导？[防断更微lxknumber1].mp4
112-A2C和A3C：如何提升基本的PolicyGradient算法[防断更微lxknumber1].mp4
113-Gumbel-trick：如何将离散的优化改变为连续的优化问题？[防断更微lxknumber1].mp4
114-MCTS简介：如何将“推理”引入到强化学习框架中[防断更微lxknumber1].mp4
115-DirectPolictyGradient：基本设定及Gumbel-trick的使用[防断更微lxknumber1].mp4
116-DirectPolictyGradient：轨迹生成方法[防断更微lxknumber1].mp4
117-AutoML及NeuralArchitectureSearch简介[防断更微lxknumber1].mp4
118-AutoML网络架构举例[防断更微lxknumber1].mp4
119-RENAS：如何使用遗传算法和增强学习探索网络架构[防断更微lxknumber1].mp4
12-深度学习与硬件：TPU[防断更微lxknumber1].mp4
120-DifferentiableSearch：如何将NAS变为可微的问题[防断更微lxknumber1].mp4
121-层次搜索法：如何在模块之间进行搜索？[防断更微lxknumber1].mp4
122-LeNAS：如何搜索搜索space[防断更微lxknumber1].mp4
123-超参数搜索：如何寻找算法的超参数[防断更微lxknumber1].mp4
124-Learningtooptimize：是否可以让机器学到一个新的优化器[防断更微lxknumber1].mp4
125-遗传算法和增强学习的结合[防断更微lxknumber1].mp4
126-使用增强学习改进组合优化的算法[防断更微lxknumber1].mp4
127-多代理增强学习概述：什么是多代理增强学习？[防断更微lxknumber1].mp4
128-AlphaStar介绍：AlphaStar中采取了哪些技术？[防断更微lxknumber1].mp4
129-IMPALA：多Agent的Actor-Critic算法[防断更微lxknumber1].mp4
13-AI项目部署：基本原则[防断更微lxknumber1].mp4
130-COMA-Agent之间的交流[防断更微lxknumber1].mp4
131-多模态表示学习简介[防断更微lxknumber1].mp4
132-知识蒸馏：如何加速神经网络推理[防断更微lxknumber1].mp4
133-DeepGBM：如何用神经网络捕捉集成树模型的知识[防断更微lxknumber1].mp4
134-文本推荐系统和增强学习[防断更微lxknumber1].mp4
135-RL训练方法集锦：简介[防断更微lxknumber1].mp4
136-RL训练方法-RL实验的注意事项[防断更微lxknumber1].mp4
137-PPO算法[防断更微lxknumber1].mp4
138-Reward设计的一般原则[防断更微lxknumber1].mp4
139-解决SparseReward的一些方法[防断更微lxknumber1].mp4
14-AI项目部署：框架选择[防断更微lxknumber1].mp4
140-ImitationLearning和Self-imitationLearning[防断更微lxknumber1].mp4
141-增强学习中的探索问题[防断更微lxknumber1].mp4
142-Model-basedReinforcementLearning[防断更微lxknumber1].mp4
143-TransferReinforcementLearning和Few-shotReinforcementLearning[防断更微lxknumber1].mp4
144-Quora问题等价性案例学习：预处理和人工特征[防断更微lxknumber1].mp4
145-Quora问题等价性案例学习：深度学习模型[防断更微lxknumber1].mp4
146-文本校对案例学习[防断更微lxknumber1].mp4
147-微服务和Kubernetes简介[防断更微lxknumber1].mp4
148-Docker简介[防断更微lxknumber1].mp4
149-Docker部署实践[防断更微lxknumber1].mp4
15-AI项目部署：微服务简介[防断更微lxknumber1].mp4
150-Kubernetes基本概念[防断更微lxknumber1].mp4
151-Kubernetes部署实践[防断更微lxknumber1].mp4
152-Kubernetes自动扩容[防断更微lxknumber1].mp4
153-Kubernetes服务发现[防断更微lxknumber1].mp4
154-KubernetesIngress[防断更微lxknumber1].mp4
155-Kubernetes健康检查[防断更微lxknumber1].mp4
156-Kubernetes灰度上线[防断更微lxknumber1].mp4
157-KubernetesStatefulSets[防断更微lxknumber1].mp4
158-Istio简介：Istio包含哪些功能？[防断更微lxknumber1].mp4
159-Istio实例和CircuitBreaker[防断更微lxknumber1].mp4
16-统计学基础：随机性是如何改变数据拟合的本质的？[防断更微lxknumber1].mp4
160-结束语[防断更微lxknumber1].mp4
17-神经网络基础：神经网络还是复合函数[防断更微lxknumber1].mp4
18-神经网络基础：训练神经网络[防断更微lxknumber1].mp4
19-神经网络基础：神经网络的基础构成[防断更微lxknumber1].mp4
20-Embedding简介：为什么Embedding更适合编码文本特征？[防断更微lxknumber1].mp4
21-RNN简介：马尔可夫过程和隐马尔可夫过程[防断更微lxknumber1].mp4
22-RNN简介：RNN和LSTM[防断更微lxknumber1].mp4
23-CNN：卷积神经网络是什么？[防断更微lxknumber1].mp4
24-环境部署：如何构建简单的深度学习环境？[防断更微lxknumber1].mp4
25-PyTorch简介：Tensor和相关运算[防断更微lxknumber1].mp4
26-PyTorch简介：如何构造Dataset和DataLoader？[防断更微lxknumber1].mp4
27-PyTorch简介：如何构造神经网络？[防断更微lxknumber1].mp4
28-文本分类实践：如何进行简单的文本分类？[防断更微lxknumber1].mp4
29-文本分类实践的评价：如何提升进一步的分类效果？[防断更微lxknumber1].mp4
30-经典的数据挖掘方法：数据驱动型开发早期的努力[防断更微lxknumber1].mp4
31-表格化数据挖掘基本流程：看看现在的数据挖掘都是怎么做的？[防断更微lxknumber1].mp4
32-Pandas简介：如何使用Pandas对数据进行处理？[防断更微lxknumber1].mp4
33-Matplotlib简介：如何进行简单的可视化分析？[防断更微lxknumber1].mp4
34-半自动特征构建方法：TargetMeanEncoding[防断更微lxknumber1].mp4
35-半自动特征构建方法：CategoricalEncoder[防断更微lxknumber1].mp4
36-半自动特征构建方法：连续变量的离散化[防断更微lxknumber1].mp4
37-半自动特征构建方法：EntityEmbedding[防断更微lxknumber1].mp4
38-半自动构建方法：EntityEmbedding的实现[防断更微lxknumber1].mp4
39-半自动特征构建方法：连续变量的转换[防断更微lxknumber1].mp4
40-半自动特征构建方法：缺失变量和异常值的处理[防断更微lxknumber1].mp4
41-自动特征构建方法：Symboliclearning和AutoCross简介[防断更微lxknumber1].mp4
42-降维方法：PCA、NMF和tSNE[防断更微lxknumber1].mp4
43-降维方法：DenoisingAutoEncoders[防断更微lxknumber1].mp4
44-降维方法：VariationalAutoEncoder[防断更微lxknumber1].mp4
45-变量选择方法[防断更微lxknumber1].mp4
46-集成树模型：如何提升决策树的效果[防断更微lxknumber1].mp4
47-集成树模型：GBDT和XgBoost的数学表达[防断更微lxknumber1].mp4
48-集成树模型：LightGBM简介[防断更微lxknumber1].mp4
49-集成树模型：CatBoost和NGBoost简介[防断更微lxknumber1].mp4
50-神经网络建模：如何让神经网络实现你的数据挖掘需求[防断更微lxknumber1].mp4
51-神经网络的构建：ResidualConnection和DenseConnection[防断更微lxknumber1].mp4
52-神经网络的构建：NetworkinNetwork[防断更微lxknumber1].mp4
53-神经网络的构建：GatingMechanism和Attention[防断更微lxknumber1].mp4
54-神经网络的构建：Memory[防断更微lxknumber1].mp4
55-神经网络的构建：ActivationFunction[防断更微lxknumber1].mp4
56-神经网络的构建：Normalization[防断更微lxknumber1].mp4
57-神经网络的训练：初始化[防断更微lxknumber1].mp4
58-神经网络的训练：学习率和Warm-up[防断更微lxknumber1].mp4
59-神经网络的训练：新的PyTorch训练框架[防断更微lxknumber1].mp4
60-Transformer：如何通过Transformer榨取重要变量？[防断更微lxknumber1].mp4
61-Transformer代码实现剖析[防断更微lxknumber1].mp4
62-xDeepFM：如何用神经网络处理高维的特征？[防断更微lxknumber1].mp4
63-xDeepFM的代码解析[防断更微lxknumber1].mp4
64-时序建模：如何用神经网络解决时间序列的预测问题？[防断更微lxknumber1].mp4
65-图嵌入：如何将图关系纳入模型？[防断更微lxknumber1].mp4
66-图网络简介：如何在图结构的基础上建立神经网络？[防断更微lxknumber1].mp4
67-模型融合基础：如何让你所学到的模型方法一起发挥作用？[防断更微lxknumber1].mp4
68-高级模型融合技巧：Metades是什么？[防断更微lxknumber1].mp4
69-挖掘自然语言中的人工特征：如何用传统的特征解决问题？[防断更微lxknumber1].mp4
70-重新审视WordEmbedding：NegativeSampling和ContextualEmbedding[防断更微lxknumber1].mp4
71-深度迁移学习模型：从ELMo到BERT[防断更微lxknumber1].mp4
72-深度迁移学习模型：RoBERTa、XLNet、ERNIE和T5[防断更微lxknumber1].mp4
73-深度迁移学习模型：ALBERT和ELECTRA[防断更微lxknumber1].mp4
74-深度迁移学习模型的微调：如何使用TensorFlow在TPU对模型进行微调[防断更微lxknumber1].mp4
75-深度迁移学习模型的微调：TensorFlowBERT代码简析[防断更微lxknumber1].mp4
76-深度迁移学习的微调：如何利用PyTorch实现深度迁移学习模型的微调及代码简析[防断更微lxknumber1].mp4
77-优化器：Adam和AdamW[防断更微lxknumber1].mp4
78-优化器：Lookahead，Radam和Lamb[防断更微lxknumber1].mp4
79-多重loss的方式：如何使用多重loss来提高模型准确率？[防断更微lxknumber1].mp4
80-数据扩充的基本方法：如何从少部分数据中扩充更多的数据并避免过拟合？[防断更微lxknumber1].mp4
81-UDA：一种系统的数据扩充框架[防断更微lxknumber1].mp4
82-LabelSmoothing和LogitSqueezing[防断更微lxknumber1].mp4
83-底层模型拼接：如何让不同的语言模型融合在一起从而达到更好的效果？[防断更微lxknumber1].mp4
84-上层模型拼接：如何在语言模型基础上拼接更多的模型？[防断更微lxknumber1].mp4
85-长文本分类：截取、关键词拼接和预测平均[防断更微lxknumber1].mp4
86-VirtualAdverserialTraining：如何减少一般对抗训练难收敛的问题并提高结果的鲁棒性？[防断更微lxknumber1].mp4
87-其他Embedding的训练：还有哪些Embedding方法？[防断更微lxknumber1].mp4
88-训练预语言模型[防断更微lxknumber1].mp4
89-多任务训练：如何利用多任务训练来提升效果？[防断更微lxknumber1].mp4
90-DomainAdaptation：如何利用其它有标注语料来提升效果？[防断更微lxknumber1].mp4
91-Few-shotLearning：是否有更好的利用不同任务的方法？[防断更微lxknumber1].mp4
92-半监督学习：如何让没有标注的数据也派上用场？[防断更微lxknumber1].mp4
93-依存分析和SemanticParsing概述[防断更微lxknumber1].mp4
94-依存分析和UniversalDepdencyRelattions[防断更微lxknumber1].mp4
95-如何在Stanza中实现DependencyParsing[防断更微lxknumber1].mp4
96-ShiftReduce算法[防断更微lxknumber1].mp4
97-基于神经网络的依存分析算法[防断更微lxknumber1].mp4
98-树神经网络：如何采用TreeLSTM和其它拓展方法？[防断更微lxknumber1].mp4
99-SemanticParsing基础：SemanticParsing的任务是什么？[防断更微lxknumber1].mp4
每天两小时，副业收入过万咨询+V.png
系统使用教程