Linked Questions
55 questions linked to/from What should I do when my neural network doesn't generalize well?
0
votes
1
answer
4k
views
Keras - text classification, overfitting, and how to improve my model? [duplicate]
i am developing a text classification neural network based on this two articles - https://github.com/jiegzhan/multi-class-text-classification-cnn-rnn https://machinelearningmastery.com/sequence-...
1
vote
1
answer
2k
views
SSD MobileNet v1 loss not converging bounding boxes all over the place [duplicate]
I've trained SSD MobileNet v2 model using Tensorflow API on my own dataset of ~4k dog pictures and it displays bounding boxes all over the place. I've trained with batch size 1.
The same dataset ...
1
vote
1
answer
1k
views
My Neural Net can overfit but not generalize [duplicate]
I have created a Neural network that gets its training data from a complicated physics simulation. I run the simulation by randomizing 7 different inputs. Each input can be 1 of 4 discrete values. I ...
- 21
0
votes
0
answers
839
views
Keras: validation loss decreases but accuracy does not increase [duplicate]
I am working on the development of a deep learning model for prediction of a disease from medical images. It is a binary classification algorithm. I am currently using a model built from scratch with ...
6
votes
1
answer
334
views
How to prevent overfitting? [duplicate]
I'm aware of the concept of overfitting in Machine Learning. The main advice for dealing with it, usually is regularization.
Is there other practical advice to avoid overfitting?
- 161
0
votes
0
answers
633
views
How can I reduce the noise of prediction graph? [duplicate]
I am trying to use LSTM to predict a time series data as you can see in the following image, the predicted graphs is very noisy:
The original data is looking like this:
That I normalized it like ...
- 141
0
votes
0
answers
468
views
How does ReLU deal with negative inputs? [duplicate]
I'm replicating this paper for my PhD, which says that they are using deep learning to predict stock returns. So the inputs are (mostly) continuous variables that can be negative and positive. Outputs ...
- 831
3
votes
1
answer
294
views
Neural Network - Estimating Non-linear function [duplicate]
I am fairly new to neural networks. I am trying to empirically show that a neural network can work better than logistic regression when the underlying function is non-linear. In my simulation study, ...
- 497
0
votes
0
answers
267
views
My CNN is not learning but just memorizing [duplicate]
So there has been similar posts but none of them solves my problem, so I decided to created a new question.
I'm working on a regression project where I intend to use CNN to predict material properties,...
- 1
1
vote
0
answers
242
views
Why is my keras resnet50 model overfitting? [duplicate]
I have applied Keras ResNet-50 on a small x-ray image dataset. I tried making layers both trainable and non-trainable, but my model validation accuracy doesn't improve above 50%.
I don't understand ...
- 121
0
votes
0
answers
130
views
Approximate output of unknown function using neural networks [duplicate]
I have a block that outputs a single value when fed with a time series containing a 1000 points.
I also have a dataset of records of about 20000 input time series (each containing a 1000 points) and ...
- 31
0
votes
0
answers
100
views
RNN Model accuracy with Training and test data [duplicate]
I am using RNN package in R to do regression. First created the model with training dataset and checked the model output using the same training dataset. It was fairly accurate with the predicted ...
0
votes
1
answer
68
views
How to prevent the keras convolutional neural network model to over-fit? [duplicate]
I want to build a convolutional neural network and train it to recognise whether the digit is 0 or 1.
Example of my training data is a 800 * 600 gray scale image containing a digit one:
I have 22 ...
- 123
0
votes
0
answers
55
views
Why am I obtaining values close to zero when using a NN for regression? [duplicate]
Here is the dataset.
I tried converting this implementation into its analog with Keras. Why are my predictions SO bad? They are almost always close to a single number. Doesn't matter if I use more ...
- 167
4
votes
0
answers
36
views
What are the most common techniqes for preventing overfitting? [duplicate]
How is this issue dealt with, in practice?
- 331