machine-learning

问题 I am following the tutorial over here : https://www.rpubs.com/loveb/som . This tutorial shows how to use the Kohonen Network (also called SOM, a type of machine learning algorithm) on the iris data. I ran this code from the tutorial: library(kohonen) #fitting SOMs library(ggplot2) #plots library(GGally) #plots library(RColorBrewer) #colors, using predefined palettes iris_complete <-iris[complete.cases(iris),] iris_unique <- unique(iris_complete) # Remove duplicates #scale data iris.sc = scale

问题 I am following the tutorial over here : https://www.rpubs.com/loveb/som . This tutorial shows how to use the Kohonen Network (also called SOM, a type of machine learning algorithm) on the iris data. I ran this code from the tutorial: library(kohonen) #fitting SOMs library(ggplot2) #plots library(GGally) #plots library(RColorBrewer) #colors, using predefined palettes iris_complete <-iris[complete.cases(iris),] iris_unique <- unique(iris_complete) # Remove duplicates #scale data iris.sc = scale

问题 I am currently experimenting with TensorFlow and machine learning, and as a challenge, I decided to try and code a machine learning software, on the Kaggle website, that can analyze brain MRI scans and predict if a tumour exists or not. I did so with the code below and began training the model. However, the text that showed up during training showed that none of the loss values (training or validation) had proper values and that the accuracies flatlined, or fluctuated between two numbers (the

问题 I am doing data augmentation using data_gen=image.ImageDataGenerator(rotation_range=20,width_shift_range=0.2,height_shift_range=0.2, zoom_range=0.15,horizontal_flip=False) iter=data_gen.flow(X_train,Y_train,batch_size=64) data_gen.flow() needs a rank 4 data matrix, so the shape of X_train is (60000, 28, 28, 1) . We need to pass the same shape i.e (60000, 28, 28, 1) while defining the architecture of the model as follows; model=Sequential() model.add(Dense(units=64,activation='relu',kernel

问题 I am doing data augmentation using data_gen=image.ImageDataGenerator(rotation_range=20,width_shift_range=0.2,height_shift_range=0.2, zoom_range=0.15,horizontal_flip=False) iter=data_gen.flow(X_train,Y_train,batch_size=64) data_gen.flow() needs a rank 4 data matrix, so the shape of X_train is (60000, 28, 28, 1) . We need to pass the same shape i.e (60000, 28, 28, 1) while defining the architecture of the model as follows; model=Sequential() model.add(Dense(units=64,activation='relu',kernel

问题 I am using StratifiedKFold to checking the performance of my classifier. I have two classes and I trying to build Logistic Regression classier. Here is my code skf = StratifiedKFold(n_splits=10, shuffle=True, random_state=0) for train_index, test_index in skf.split(x, y): x_train, x_test = x[train_index], x[test_index] y_train, y_test = y[train_index], y[test_index] tfidf = TfidfVectorizer() x_train = tfidf.fit_transform(x_train) x_test = tfidf.transform(x_test) clf = LogisticRegression(class

问题 I am using StratifiedKFold to checking the performance of my classifier. I have two classes and I trying to build Logistic Regression classier. Here is my code skf = StratifiedKFold(n_splits=10, shuffle=True, random_state=0) for train_index, test_index in skf.split(x, y): x_train, x_test = x[train_index], x[test_index] y_train, y_test = y[train_index], y[test_index] tfidf = TfidfVectorizer() x_train = tfidf.fit_transform(x_train) x_test = tfidf.transform(x_test) clf = LogisticRegression(class

问题 Here is the config of my model : "model": { "loss": "categorical_crossentropy", "optimizer": "adam", "layers": [ { "type": "lstm", "neurons": 180, "input_timesteps": 15, "input_dim": 103, "return_seq": true, "activation": "relu" }, { "type": "dropout", "rate": 0.1 }, { "type": "lstm", "neurons": 100, "activation": "relu", "return_seq": false }, { "type": "dropout", "rate": 0.1 }, { "type": "dense", "neurons": 30, "activation": "relu" }, { "type": "dense", "neurons": 3, "activation": "softmax"

问题 I made the following architecture Layer (type) Output Shape Param # ================================================================= embedding_7 (Embedding) (None, 50, 64) 512000 _________________________________________________________________ bidirectional_5 (Bidirection (None, 200) 132000 _________________________________________________________________ dense_9 (Dense) (None, 1) 201 ================================================================= Total params: 644,201 Trainable params:

问题 I recently learned about the following phenomenon: Google BERT word embeddings of well-known state-of-the-art models seem to ignore the measure of semantical contrast between antonyms in terms of the natural distance(norm2 or cosine distance) between the corresponding embeddings. For example: The measure is the "cosine distance" (as oppose to the "cosine similarity"), that means closer vectors are supposed to have smaller distance between them. As one can see, BERT states "weak" and "powerful