동선생

[NLP] 2. NLP Arrangement of Terms (용어 정리)

This post heavily relies on the book 'Natural Language Processing with Pytorch':https://books.google.co.kr/books?id=AIgxEAAAQBAJ&printsec=copyright&redir_esc=y#v=onepage&q&f=falseCorpusAll NLP tasks begin with text data called a corpus(corpa in plural).A corpus typically includes raw text (in ASCII or UTF-8 format) and metadata associated with this text. While raw text is a sequence of character..

[Kaggle Study] 16. Translation Invariance

Translation InvarianceTranslation invariance in CNN means that even if the input position changes, the output maintains the same value.Actually, CNN networks themselves have translation equivariance (variance).Meaning that, when computing with convolution filters, if the position of a specific feature changes, the position of that feature's computation result in the output naturally changes as w..

[Kaggle Study] 15. Why Use Convolutional Layer?

This post heavily relies on Andrew Ng's lecture: 컨볼루션 신경망DeepLearning.AI에서 제공합니다. 딥러닝 전문 과정의 네 번째 과정에서는 컴퓨터 비전이 어떻게 발전해 왔는지 이해하고 자율주행, 얼굴 인식, 방사선 이미지 판독 등 흥미로운 응용 분야에 익숙해www.coursera.orgAdvantages of Convolutional Layers Over Fully Connected LayersFollowing above example, if we use Fully-connected layer instead of Convolutional layer, we should connect 3,072 and 4,704 neurons.That is, the number..

[Kaggle Study] #2 Porto Seguro's Safe Driver Prediction

Second competition following Yuhan Lee's kaggle curriculum. Binary classification competition using tabular data.First KernelData preparation and exploration kernel.Insights / Summary:1.info method (e.g. train.info()) provides data type, null value existence, number of rows of each variable of the dataframe.2. Storing metadata for each variable might help data management.Code example:data = []fo..

This post heavily relies on the book 'Natural Language Processing with Pytorch':https://books.google.co.kr/books?id=AIgxEAAAQBAJ&printsec=copyright&redir_esc=y#v=onepage&q&f=falseNLP?A set of techniques that solve practical problems using statistical methods to understand text, regardless of linguistic knowledge.The 'understanding' of text is mainly achieved by converting text into computable re..

Multiclass Classification can be divided into 2 categories: ordinal classification and nominal classification.For nominal(명목형) classification problems, you can think of a multiclass classification algorithm that outputs probability distributions like [0.7, 0.1, 0.2] for distinguishing between car, human, and tree.For ordinal classification, you can think of a problem that categorizes a child's c..

Hyperparameter Tuning?The process of adjusting hyperparameters to optimize the model for better performanceThere are certain hyperparameters that have higer tuning priority than others.In other words, some hyperparameters can work well with commonly known values without tuning, while others require tuning to determine which values work best.There are various tuning methods such as:Manual SearchG..

This post heavily relies on Andrew Ng's lecture: 심층 신경망 개선하기: 하이퍼파라미터 튜닝, 정규화 및 최적화DeepLearning.AI에서 제공합니다. 딥러닝 스페셜라이제이션의 두 번째 과정에서는 딥러닝 블랙박스를 열어 성능을 향상시키고 좋은 결과를 도출하는 프로세스를 체계적으로 이해합니다. 딥러닝 애www.coursera.orgNormalizationNormalization(정규화) 은 training process의 속도를 높여주는 기법들 중 하나입니다. 주의 해야할 점 중 하나는 test set에도 같은 mean, variance 값을 사용하여 정규화해줘야 올바른 test 결과값이 나온다는 것입니다.Unnormalized cost function과 Norma..

Early stopping is a technique used while training neural networks to prevent the model from overfitting.It basically stops the training process before the model starts to overfit.We monitor the model's performance on a validation set during the training process and stop the training process when the general performance starts to degrade, which indicates that the model is beginning to overfit the..

Deep learning fundamentally requires a large amount of data for effective training.Additionally, to solve the chronic problem of overfitting in deep learning, it needs sufficient high-quality data.However, increasing the amount of data requires significant cost and time, and in some cases, it can be difficult to even collect or process the data.To address this issue, various Data Augmentation te..