bf intorg YOLOv8开发
bf intorg YOLOv8 dev (2024-01-19, Jupyter Notebook, 0KB, 下载0次)
利用乳腺癌-威斯康星（诊断）数据集，多层感知器（MLP）神经网络在二元分类（恶性与良性）中达到97.66%的准确率。为了获得鲁棒的模型性能，采用了正则化技术，包括丢失层和L1正则化。
Utilizing the Breast Cancer Wisconsin (Diagnostic) Dataset, a Multi-Layer Perceptron (MLP) neural network achieved 97.66% accuracy in binary classification (Malignant vs. Benign). Regularization techniques, including dropout layers and L1 regularization, were employed for robust model performance. (2024-01-06, Jupyter Notebook, 0KB, 下载0次)
探索此MNIST手写分类项目，实现97.61%的准确性。通过relu和softmax激活、Adam优化器和稀疏分类交叉熵损失实现。深入研究代码，以深入了解模型的性能。
Explore this MNIST Handwritten Classification project achieving 97.61% accuracy. Implemented with relu and softmax activations, Adam optimizer, and sparse_categorical_crossentropy loss. Dive into the code for insights into the model s performance. (2024-01-06, Jupyter Notebook, 0KB, 下载0次)
基于EfficientNet_B7的阿拉伯字母模型，测试准确率为97.04%
EfficientNet_B7 based model for Arabic letters with 97.04% test accuracy (2023-12-24, Jupyter Notebook, 0KB, 下载0次)
Sistem ini dibangun menggunakan算法卷积神经网络Degan akurasi sebesar 97%。
Sistem ini dibangun menggunakan algortima Convolutional Neural Network dengan akurasi sebesar 97%. (2023-12-07, Jupyter Notebook, 0KB, 下载0次)
决策树和MLP分类器比较
Decision Tree and MLP Classifiers comparison (2023-12-01, Jupyter Notebook, 0KB, 下载0次)
深度学习A1，
Deep Learning A1, (2023-10-11, Jupyter Notebook, 0KB, 下载0次)
该模型在所有25000个样本上训练，我们达到了97.6%的准确性。，
The model trained on all 25,000 samples, we reach 97.6% accuracy., (2020-08-24, Jupyter Notebook, 0KB, 下载0次)
使用PCA进行降维，
Dimensionality Reduction Using PCA, (2023-09-21, Jupyter Notebook, 0KB, 下载0次)
在花卉数据集上评估预训练的VGG16分类模型，获得97.37%的准确率，并用早期...，
Evaluated pre-trained VGG16 classification model on flower dataset to get 97.37% accuracy, and built VGG16 model from scratch with early stopping to get 76% accuracy. (2023-09-05, Jupyter Notebook, 0KB, 下载0次)
使用经典机器学习识别手写数字，准确率为97%，f1得分
Recognizing handwritten digits with classical machine learning with a 97% accuracy and f1-score (2023-08-14, Jupyter Notebook, 0KB, 下载0次)
The code is followed the instruction by https://leemeng.tw/attack_on_bert_transfer_learning_in_nlp.html#%E7%94%A8-BERT-fine-tune-%E4%B8%8B%E6%B8%B8%E4%BB%BB%E5%8B%99,stars:1, update:2022-01-09 16:55:37
The code is followed the instruction by <a href="https://leemeng.tw/attack_on_bert_transfer_learning_in_nlp.html#%E7%94%A8-BERT- fine-tune-%E4%B8%8B%E6%B8%B8%E4%BB%BB%E5%8B%99" rel="nofollow">https://leemeng.tw/attack_on_bert_transfer_learning_in_nlp.html#%E7%94%A8-BER...</a> , stars:1, update:2022-01-09 16:55:37 (2023-06-25, Jupyter Notebook, 10KB, 下载0次)
在ResNet-50上微调的胡须分类器，以97%的准确性对胡须进行分类！
A beard classifier fine-tuned on ResNet-50 that classifies beard with 97% accuracy! (2021-01-02, Jupyter Notebook, 28KB, 下载0次)
使用深度神经网络和卷积神经网络对交通标志进行分类。准确度约为97.5%。
Classify Traffic Signs with deep neural networks & convolutional neural networks. Accuracy roughly 97.5%. (2017-02-22, Jupyter Notebook, 35847KB, 下载0次)
您的新闻文章、博客、YouTube视频、学习材料、维基百科内容等的全合一摘要。
An All-in-1 summarizer for your news articles, blogs, YouTube videos, study materials, Wikipedia content, etc. (2022-10-25, Jupyter Notebook, 180KB, 下载0次)
数据512 A1:_Data_curation
Data 512 A1:_Data_curation (2019-10-17, Jupyter Notebook, 962KB, 下载0次)
使用暹罗神经网络来实现少镜头学习过程，以实现惊人的97%的分类精度...
Using Siamese Neural networks to implement few shot learning process to achieve an amazing 97% accuracy in classifying real vs forged signatures. (2020-11-03, Jupyter Notebook, 2225KB, 下载0次)
这是我的第一个很好的机器学习模型，这个模型在猫和狗之间的分类准确率为97.85%。...
This is my first nice machine learning model, This model gave a 97.85% accuracy in classifying between Cats and Dogs. I made it using a pre-trained base model MobileNet V2 , and after that i added a global average pooling and then a dense layer for categorization between two classes ( cats and dogs) , i used only one dense neuron in last layer (2020-07-27, Jupyter Notebook, 1118KB, 下载0次)
数据可视化，准确度为0.97
data visualization ,and accuracy is 0.97 (2019-05-07, Jupyter Notebook, 744KB, 下载0次)
使用陀螺仪和加速度计变量的神经网络人类活动识别，验证精度在KAGGLE上最好。人工神经网络具有97.98%的验证准确率和预测精度...
The VALIDATION ACCURACY is BEST on KAGGLE. Artificial Neural Network with a validation accuracy of 97.98 % and a precision of 95% was achieved from the data to learn (as a cellphone attached on the waist) to recognise the type of activity that the user is doing. The dataset s description goes like this: The sensor signals (accelerometer and (2018-10-02, Jupyter Notebook, 1174KB, 下载0次)