¡Hola, Mundo!

Loss function In deep learning, we typically use a gradient-based optimization strategy to train a model HTML 삽입 미리보기할 수 없는 소스 using some loss function HTML 삽입 미리보기할 수 없는 소스 are some input-output pair. It is used to help the model determine how "wrong" it is and, based on that "wrongness," improve itself. It's a measure of error. Our goal throughout training is to minimize this error/loss. https..

Activation function It takes the output of a neuron and decide whether this neuron is going to fire or not, in other words, "should this neuron 'fire' or not?" Activation function Step function Hardly used. Sigmoid function Used in Binary Classification. Used in output layer usually. Vanishing Gradient possible. ↓ Hyperbolic tangent function ReLU(Rectified Linear Unit) function f(x) = max(0,x) I..

vocabulary_ Mapping all the words with integers. text=["Don't be fooled by the dark sounding name, Mr. Jone's Orphanage is as cheery as cheery goes for a pastry-shop."] vector=CountVectorizer() # Or TfidfVectorizer() print(vector.vocabulary_) >>> {'don': 5, 'be': 1, 'fooled': 6, 'by': 2, 'the': 17, 'dark': 4, 'sounding': 16, 'name': 12, 'mr': 11, 'jone': 10, 'orphanage': 13, 'is': 9, 'as': 0, 'c..

Keras 1. Preprocessing from tensorflow.keras.preprocessing.text import Tokenizer t=Tokenizer() fit_text='The earth is an awesome place live' t.fit_on_texts([fit_text]) test_text='The earth is an great place live' sequences=t.texts_to_sequences([test_text])[0] sequences >>>[1, 2, 3, 4, 6, 7] t.word_index >>>{'an': 4, 'awesome': 5, 'earth': 2, 'is': 3, 'live': 7, 'place': 6, 'the': 1} Tokenizer.fi..

Dropout - One way to avoid overfitting, using several neurons only rather than whole neurons when machine training. - It does not have any learnable parameters and has only one hyperparameter. - It does not behave similarly during training and testing. To be understand this, let us consider a simple fully connected layer containing 10 neurons. We are using a dropout probability of 0.5. Well duri..