Questions tagged [continual-learning]
6 questions
9
votes
4 answers
Why is Permuted MNIST good for evaluating continual learning models?
While I was reading papers about continual learning, I found that many researchers use permutated MNIST to evaluate their approach.
I understand what it is but it is not clear to me why they use it?
What I understand is that they were trying to…
Imtk
- 135
- 1
- 7
2
votes
1 answer
Bayes rule when data $D$ is split into two independent parts: $D_a, D_b$
In this machine learning paper Overcoming catastrophic forgetting in neural
networks, they present to you equation 1, the log of bayes rule:
$$ \log p(\theta|D) = \log p(D|\theta) + \log p(\theta) - \log p(D) \quad (1)$$
Where $\theta$ are the…
clam
- 198
- 2
- 6
2
votes
2 answers
Parallel multi-task learning vs. continual learning
Assuming we want to learn k tasks jointly, and the data for all tasks are available. We may either train a model with parallel multi-task learning (eg. each batch is a mixture of samples from the k tasks), or present tasks sequentially (eg. switch…
thinkbear
- 141
- 5
1
vote
0 answers
Federated Learning and Continual Learning: Non-IID Learning
I have some exposure to federated learning and continual learning which are non-iid learning instances [1] and [2] I was wondering can we state the following:
Federated learning is when the dataset is distributed in a non-iid
manner over space…
Complicated
- 33
- 4
1
vote
0 answers
Which metrics should be used in preprocessing in continual learning?
So my idea is to train an LSTM - autoencoder for anomaly detection by continual learning, i.e., I want to update the model after each 10 time steps. Firstly I will train it on source data, then re-train on first batch of new data and then re-train…
pikachu
- 731
- 2
- 10
0
votes
0 answers
How would I go about implementing continual learning in a supervised multi-output regression problem?
I want to implement a regressor (such as a neural network) with multiple outputs, based on a vector of inputs. It would be trained on a big initial dataset, before being used by some human user.
This regressor should be able to receive some feedback…
Andrei Miculiță
- 1
- 1