All Projects → myazi → myDL

myazi / myDL

Licence: other
Deep Learning

Programming Languages

python
139335 projects - #7 most used programming language
C++
36643 projects - #6 most used programming language

Projects that are alternatives of or similar to myDL

Pytorch Kaldi
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
Stars: ✭ 2,097 (+11550%)
Mutual labels:  dnn, lstm, gru, rnn
Pytorch Rnn Text Classification
Word Embedding + LSTM + FC
Stars: ✭ 112 (+522.22%)
Mutual labels:  lstm, gru, rnn
See Rnn
RNN and general weights, gradients, & activations visualization in Keras & TensorFlow
Stars: ✭ 102 (+466.67%)
Mutual labels:  lstm, gru, rnn
tf-ran-cell
Recurrent Additive Networks for Tensorflow
Stars: ✭ 16 (-11.11%)
Mutual labels:  lstm, gru, rnn
Pytorch-POS-Tagger
Part-of-Speech Tagger and custom implementations of LSTM, GRU and Vanilla RNN
Stars: ✭ 24 (+33.33%)
Mutual labels:  lstm, gru, rnn
Rnn Notebooks
RNN(SimpleRNN, LSTM, GRU) Tensorflow2.0 & Keras Notebooks (Workshop materials)
Stars: ✭ 48 (+166.67%)
Mutual labels:  lstm, gru, rnn
Eeg Dl
A Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow.
Stars: ✭ 165 (+816.67%)
Mutual labels:  lstm, gru, rnn
Easy Deep Learning With Keras
Keras tutorial for beginners (using TF backend)
Stars: ✭ 367 (+1938.89%)
Mutual labels:  lstm, gru, rnn
Rnn ctc
Recurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.
Stars: ✭ 220 (+1122.22%)
Mutual labels:  lstm, gru, rnn
Pytorch Seq2seq
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
Stars: ✭ 3,418 (+18888.89%)
Mutual labels:  lstm, gru, rnn
Ailearning
AiLearning: 机器学习 - MachineLearning - ML、深度学习 - DeepLearning - DL、自然语言处理 NLP
Stars: ✭ 32,316 (+179433.33%)
Mutual labels:  dnn, lstm, rnn
ConvLSTM-PyTorch
ConvLSTM/ConvGRU (Encoder-Decoder) with PyTorch on Moving-MNIST
Stars: ✭ 202 (+1022.22%)
Mutual labels:  lstm, gru, rnn
Load forecasting
Load forcasting on Delhi area electric power load using ARIMA, RNN, LSTM and GRU models
Stars: ✭ 160 (+788.89%)
Mutual labels:  lstm, gru, rnn
Haste
Haste: a fast, simple, and open RNN library
Stars: ✭ 214 (+1088.89%)
Mutual labels:  lstm, gru, rnn
theano-recurrence
Recurrent Neural Networks (RNN, GRU, LSTM) and their Bidirectional versions (BiRNN, BiGRU, BiLSTM) for word & character level language modelling in Theano
Stars: ✭ 40 (+122.22%)
Mutual labels:  lstm, gru, rnn
LearningMetersPoems
Official repo of the article: Yousef, W. A., Ibrahime, O. M., Madbouly, T. M., & Mahmoud, M. A. (2019), "Learning meters of arabic and english poems with recurrent neural networks: a step forward for language understanding and synthesis", arXiv preprint arXiv:1905.05700
Stars: ✭ 18 (+0%)
Mutual labels:  dnn, lstm, gru
QTextRecognizer
A gui for tesseractOCR with some preprocessing image options (OpenCV) for improve character recognition
Stars: ✭ 27 (+50%)
Mutual labels:  dnn, lstm
EBIM-NLI
Enhanced BiLSTM Inference Model for Natural Language Inference
Stars: ✭ 24 (+33.33%)
Mutual labels:  lstm, rnn
LSTM-GRU-from-scratch
LSTM, GRU cell implementation from scratch in tensorflow
Stars: ✭ 30 (+66.67%)
Mutual labels:  lstm, gru
5baa61e4c9b93f3f0682250b6cf8331b7ee68fd8
RNN-LSTM that learns passwords from a starting list
Stars: ✭ 35 (+94.44%)
Mutual labels:  lstm, rnn
    1.DNN 可设置网络结构参数,层数,神经元个数,激活函数

--------------------------------------------------------

    2.初始化: Random,"he","arXiv"
    
    3.方差/偏差: Regularization, Dropout
    
    4 随机采样: Stochastic gradient descent,mini-batch
    
    5 优化方法: Gradient Descent,Momentum Gradient Descent,Adam
    
    6 矩阵库更新: 主要考虑内存分配问题,但存在申请内存失败问题
    
--------------------------------------------------------------------
    1 深度神经网络: C++/python/TF 实现
    
    2 卷积神经网络: python/TF 实现
    
    3 序列模型: python/TF 实现 (RNN GRU LSTM)  
    
    4 DeepLearing学习笔记:
提纲
1神经网络构建
	1.1神经网络基础
		逻辑回归模型,Softmax,矩阵形式表示
	1.2 神经网络的前向传递和反向传播的数学推导
		线性,激活函数,损失函数,需要注意的是数据表示,维度问题
2 改善神经网络
	2.1 防止过拟合  提前结束, 增加训练样本, 正则项, Dropout
	2.2 梯度消失问题  初始化,梯度剪辑,激活函数, Batch-Norm,Res-net,LSTM
	2.3 优化方法(加速 学习率)  Mini-batch,动量的梯度下降,RMS-prop,Adam
	2.4 梯度检验, 调参(网络结构:层,神经元个数;学习率: ;优化方法: ;正则化项: ;Dropout;Mini-batch size;迭代次数;初始化方式)
3 结构化机器学习
	3.1 快速搭建好第一个系统:框架使用,开源使用, 迁移学习,数据预处理
	3.2 误差分析:偏差和方差分析,正交化调试,控制变量法调试	
		1 偏差问题,调整网络架构,学习率,优化方法,增加数据集
        	2 方差问题(过拟合),正则化,Dropout,增加训练集
        	3 真实数据场景差 真实数据与训练测试数据分布不一致
    	3.3 单一评价标准,如F1值结合了精度和召回率
4 卷积神经网络
	4.1 卷积,池化,填充,全连接概念以及超参数和参数(参数共享,特征提取思想)
	4.2 CNN构建的流程以及数学表示形式,需要注意的是,数据表示,维度问题
        	1 卷积,Relu,池化,向量化,全连接,Softmax层,前向传播
        	2 卷积,池化,全连接,Softmax层,链式求导
	4.3 经典的CNN架构
		LeNet-5,AlexNet,VGG(卷积核大小统一化),Resnet(解决梯度消失问题),Inception(可学习卷积核大小),迁移学习构建初始网络架构
5 序列模型
	5.1 序列模型架构:many-to-many(实体识别,机器翻译), many-to-one(情感分类),one-to-many(语音生成),one-to-one
	5.2 网络架构:RNN,GRU,LSTM,B-RNN,D-RNN 前向反向数学推导,需要注意的是数据表示,维度问题
	5.3 Embeding:上下文关系学习词向量(*),skipgram,负采用,Glove词向量,去偏见,注意力机制(上下文加权)
    
 

    
    

    
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].