Pinned Repositories
AiLearning
AiLearning: 机器学习 - MachineLearning - ML、深度学习 - DeepLearning - DL、自然语言处理 NLP
con_jisuan_guocheng_keshihua
A technical report on convolution arithmetic in the context of deep learning
Crack_Detection_Detectron2
Deep-Learning-with-TensorFlow-book
深度学习入门开源书，基于TensorFlow 2.0案例实战。Open source Deep Learning book, based on TensorFlow 2.0 framework.
Dive-into-DL-PyTorch
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。
dragen1860-Deep-Learning-with-TensorFlow-book
early-stopping-pytorch
Early stopping for PyTorch
eat_tensorflow2_in_30_days
Tensorflow2.0 🍎🍊 is delicious, just eat it! 😋😋
python_data_analysis_and_mining_action
《python数据分析与挖掘实战》的代码笔记
SSA-DBN-classification
Combining the advantages of deep belief network (DBN) in extracting features and processing high-dimensional and non-linear data, a classification method based on deep belief network is proposed. This method uses the Fourier spectrum (FFT) of the original time domain signal to train a deep confidence network through deep learning. Its advantage is that the method does not need to set parameters when performing FFT on the signal, and directly uses all spectral components for modeling, so there is no need for complexity The feature selection method has strong versatility and adaptability. Finally, in order to further enhance the classification accuracy of DBN, the Sparrow Search Algorithm (SSA) is used to optimize the weight parameters of DBN. The experimental results show that the method proposed in this paper can effectively improve the classification and recognition accuracy.
ZMLloveMLN's Repositories
ZMLloveMLN/SSA-DBN-classification
Combining the advantages of deep belief network (DBN) in extracting features and processing high-dimensional and non-linear data, a classification method based on deep belief network is proposed. This method uses the Fourier spectrum (FFT) of the original time domain signal to train a deep confidence network through deep learning. Its advantage is that the method does not need to set parameters when performing FFT on the signal, and directly uses all spectral components for modeling, so there is no need for complexity The feature selection method has strong versatility and adaptability. Finally, in order to further enhance the classification accuracy of DBN, the Sparrow Search Algorithm (SSA) is used to optimize the weight parameters of DBN. The experimental results show that the method proposed in this paper can effectively improve the classification and recognition accuracy.
ZMLloveMLN/AiLearning
AiLearning: 机器学习 - MachineLearning - ML、深度学习 - DeepLearning - DL、自然语言处理 NLP
ZMLloveMLN/early-stopping-pytorch
Early stopping for PyTorch
ZMLloveMLN/python_data_analysis_and_mining_action
《python数据分析与挖掘实战》的代码笔记
ZMLloveMLN/con_jisuan_guocheng_keshihua
A technical report on convolution arithmetic in the context of deep learning
ZMLloveMLN/Crack_Detection_Detectron2
ZMLloveMLN/Deep-Learning-with-TensorFlow-book
深度学习入门开源书，基于TensorFlow 2.0案例实战。Open source Deep Learning book, based on TensorFlow 2.0 framework.
ZMLloveMLN/Dive-into-DL-PyTorch
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。
ZMLloveMLN/dragen1860-Deep-Learning-with-TensorFlow-book
ZMLloveMLN/eat_tensorflow2_in_30_days
Tensorflow2.0 🍎🍊 is delicious, just eat it! 😋😋
ZMLloveMLN/GitHub520
:kissing_heart: 让你“爱”上 GitHub，解决访问时图裂、加载慢的问题。（无需安装）
ZMLloveMLN/imgyaso
提供多种图像处理工具，包括自适应二值化，灰度网格仿色，扩散仿色，和颜色缩减。
ZMLloveMLN/Interview
Interview = 简历指南 + LeetCode + Kaggle
ZMLloveMLN/kafka-doc-zh
Kafka 中文文档
ZMLloveMLN/MLN
Not alone
ZMLloveMLN/netron
Visualizer for neural network, deep learning and machine learning models
ZMLloveMLN/nlp-pytorch-zh
《Natural Language Processing with PyTorch》中文翻译
ZMLloveMLN/opencv-doc-zh
:book: [译] OpenCV 中文文档
ZMLloveMLN/Projects
ZMLloveMLN/Python
最良心的 Python 教程：
ZMLloveMLN/StevenLei2017-AI_projects
ZMLloveMLN/VMD-SSA-LSSVM-for-power-forecast
In this paper, LSSVM is used for short-term power load forecasting, and a short-term power load forecasting model based on LSSVM is proposed. At the same time, a Sparrow Algorithm (SSA) model is established to optimize the parameters of LLSVM to improve the forecasting accuracy. However, studies have shown that if a time series forecast model is built directly on the original series, the forecast data will lag the actual data. Such a model is meaningless. This is mainly due to the autocorrelation in the time series data, so I use VMD decomposition The method decomposes the original sequence, then models each sequence separately, and finally adds the results of each sequence test set as the final result. The comparative analysis results show that the prediction accuracy of this model is better than that of many other prediction models, and this model shows better performance in short-term load forecasting.
ZMLloveMLN/Yolo_3_deep_sort_object_tracking
基于yolo3_deep_sort的目标检测与追踪