Recent questions tagged machine

0 votes

1.1k views

1 answer

machine learning - ResNet: 100% accuracy during training, but 33% prediction accuracy with the same data

I am new to machine learning and deep learning, and for learning purposes I tried to play with Resnet. I tried to ... ? and how can that happen? See Question&Answers more detail:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - How to create a new gym environment in OpenAI?

I have an assignment to make an AI Agent that will learn to play a video game using ML. I want to create ... without the help of OpenAI Gym? See Question&Answers more detail:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

machine learning - Should Feature Selection be done before Train-Test Split or after?

Actually, there is a contradiction of 2 facts that are the possible answers to the question: The conventional ... single test/unknown instance. See Question&Answers more detail:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

machine learning - What is the difference between a sigmoid followed by the cross entropy and sigmoid_cross_entropy_with_logits in TensorFlow?

When trying to get cross-entropy with sigmoid activation function, there is a difference between loss1 = -tf.reduce_sum(p ... loss1, " ", loss2) See Question&Answers more detail:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

machine learning - Why should weights of Neural Networks be initialized to random numbers?

Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers. Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - Intuitive understanding of 1D, 2D, and 3D convolutions in convolutional neural networks

Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers. Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - Epoch vs Iteration when training neural networks

Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers. Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.3k views

1 answer

machine learning - Is there a rule-of-thumb for how to divide a dataset into training and validation sets?

Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers. Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

machine learning - How to interpret caffe log with debug_info?

When facing difficulties during training (nans, loss does not converge, etc.) it is sometimes useful to look at more ... 6.11659, 4085.07) What does it mean? Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - Python: tf-idf-cosine: to find document similarity

I was following a tutorial which was available at Part 1 & Part 2. Unfortunately the author didn't have the ... am not sure how to identify the two vectors. Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - Many to one and many to many LSTM examples in Keras

I try to understand LSTMs and how to build them with Keras. I found out, that there are principally the 4 ... tasks, maybe with a little bit of explanation. Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.0k views

1 answer

machine learning - Why binary_crossentropy and categorical_crossentropy give different performances for the same problem?

I'm trying to train a CNN to categorize text by topic. When I use binary cross-entropy I get ~80% ... results with binary, and poor results with categorical. Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - What is the role of the bias in neural networks?

Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers. Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

machine instruction - How was the first compiler written?

I heard about the chicken and the egg and bootstrapping. I have a few questions. What wrote the first compiler ... to believe they wrote a compiler in binary. Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - Why do we have to normalize the input for an artificial neural network?

Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers. Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - Common causes of nans during training

I've noticed that a frequent occurrence during training is NANs being introduced. Often times it seems to be ... combatting this (and why do they work)? Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

machine learning - What is a `"Python"` layer in caffe?

Caffe has a layer type "Python". For instance, this layer type can be used as a loss layer. On other occasions ... this layer type? How can this layer be used? Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - Clarification on a Neural Net that plays Snake

I'm new to neural networks/machine learning/genetic algorithms, and for my first implementation I am writing a network ... the fitness to help that? Thank you! Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

machine learning - How to serve a Spark MLlib model?

I'm evaluating tools for production ML based applications and one of our options is Spark MLlib , but I have ... you serve/deploy ML models in Apache Spark ? Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

machine learning - Python NLTK pos_tag not returning the correct part-of-speech tag

Having this: text = word_tokenize("The quick brown fox jumps over the lazy dog") And running: nltk.pos_tag( ... brown and fox should be adjectives not nouns. Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - How does the Google "Did you mean?" Algorithm work?

Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers. Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - What function defines accuracy in Keras when the loss is mean squared error (MSE)?

How is Accuracy defined when the loss function is mean square error? Is it mean absolute percentage error? The model I use ... 36 - loss: 5.0148 - acc: 0.2306 Question&Answers:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.5k views

1 answer

machine learning - What is switchable atrous convolution and why we use it?

I was trying to understand a research paper called "DetectoRS: Detecting Objects with Recursive Feature Pyramid and ... -is-switchable-atrous-convolution-and-why-we-use-it...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.3k views

1 answer

machine learning - Weird spikes in Loss function - Cross Validated

question from:https://stackoverflow.com/questions/65833756/weird-spikes-in-loss-function...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

machine learning - How to save large sklearn RandomForestRegressor model for inference

I trained a Sklearn RandomForestRegressor model on 19GB of training data. I would like to save it to ... /how-to-save-large-sklearn-randomforestregressor-model-for-inference...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - Add conditioning variables to a random forest model in R

I want to train a random forest to make a categorical prediction. If I want to include a fixed set of ... /65835383/add-conditioning-variables-to-a-random-forest-model-in-r...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - Why does my LSTM model work for any batch size OTHER THAN 1?

I created the following LSTM model and then I tried to find the best batch size. Surprisingly the model works very good ... does-my-lstm-model-work-for-any-batch-size-other-than-1...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

machine learning - Gradient function not able to find optimal theta but normal equation does

I tried implementing my own linear regression model in octave with some sample data but the theta does not seem to ... -not-able-to-find-optimal-theta-but-normal-equation-does...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

Categories

Just Browsing Browsing

Most popular tags