Questions tagged [multitask-learning]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
12
votes
1answer
7k views

Multi task learning in Keras

I am trying to implement shared layers in Keras. I do see that Keras has keras.layers.concatenate, but I am unsure from documentation about its use. Can I use it to ...
6
votes
2answers
81 views

Error on multitask neural nets where all outputs not observed for every example

Let's say I have 2 datasets, each from a set of experiments. Dataset A measures a set of properties X for set S, while dataset B measures properties Y for set T. X and Y are highly correlated, and S ...
5
votes
4answers
5k views

Multi target classification for different types of target variables

I am new to machine learning and I got this task in my university. I have a dataset with over 100 columns and two target variables: $target1$ is categorical i.e. $0$ or $1$ and $target2$ is continuous ...
5
votes
1answer
2k views

How to do multitask learning using Caffe?

I wonder how to do multitask learning using Caffe. Should I simply use the output layer SigmoidCrossEntropyLoss or EuclideanLoss, and define more than one outputs? E.g. is the following architecture ...
4
votes
1answer
907 views

Thoughts on improving the Multitask Learning Model

Any Thoughts on improving the Model. So far i was able to achieve around accuracy 0.20 on each task specific dense network of a Multi task Learning Architecture. I have posted model and validation ...
3
votes
1answer
304 views

Should I rescale losses before combining them for multitask learning?

I have a multitask network taking one input and trying to achieve two tasks (with several shared layers, and then separate layers). One task is multiclass classification using the CrossEntropy loss, ...
3
votes
1answer
445 views

Multi-task learning for Multi-label classification?

I have a multi-label classification problem wherein each example can belong to one of the pre-defined classes (or can belong to none of them). I was wondering if I can somehow apply multi-task ...
2
votes
1answer
761 views

Missing outputs in multiple-output neural net

I am looking at a task, where I want to predict multiple things from an image (an animal's breed [categorical], age [continuous number] and gender [categorical]). Unsurprisingly, my first thought was ...
2
votes
3answers
1k views

Multi-Source Time Series Data Prediction

I was wondering if anyone has experience with time series prediction for data from multiple sources. So for instance, time series $a,b,..,z$ each have their own shape, some may be correlated with ...
1
vote
1answer
2k views

Multi task learning architecture for Multi-label classification

I am working a classification problem. The dataset was collected from Painters by number, a competition hosted by kaggle. The task is to identify painter,style and genre given paintings. So far, I ...
1
vote
1answer
205 views

Combining heterogeneous data sets for more powerful machine learning

Suppose we have two data sets of movie reviews; one from IMDB and one from Rotten Tomatoes (RT). Each entry has a written-review and a score attached to it. The concatenated datasets might look like ...
1
vote
1answer
660 views

Multitask learning NN only trains on a few tasks

I am fairly new to the Machine Learning field, but I am working on building a multi-task network for a project I am working on. Unfortunately, despite all my best googling and digging through ...
0
votes
1answer
621 views

Implementing Multitask Classification in Keras

I am Trying to implement Multitask Learning in Keras with share constitutional Layers and task specific FC layers. Following is my model: ...
0
votes
0answers
17 views

Confusion Matrix for Multi task Learning using custom data generator

I am working on developing an MTL model. There are two tasks in the model, task1, and task2. And I have used a custom data generator using following code: ...
0
votes
0answers
15 views

Data Loader (imbalanced classes) for Multitask Learning - same input multiple output

I am working on developing an MTL model. There are three tasks in the model, task1, task2, and task3. The classes in these tasks are imalanced and I am stuck at how I should sample from these so that ...
0
votes
0answers
10 views

Multitask learning model with variable number of tasks

This is my basic multitask learning model, and it has 2 tasks. Since there are only 2 tasks, maybe I can duplicate the code for each task as self.tower1 and self.tower2. ...
0
votes
1answer
88 views

ImageDataGenerator for multi task output in Keras using flow_from_directory

I am creating a multitask CNN model and I have two different classification properties (one with 10 classes, 2nd with 5 classes) and my directory structure looks like this: ...
0
votes
1answer
806 views

How to feed data to multi-output Keras model from a single TFRecords file

I know how to feed data to a multi-output Keras model using numpy arrays for the training data. However, I have all my data in a single TFRecords file comprising several feature columns: an image, ...
0
votes
0answers
20 views

How to optimize neural network with mutile losses

There is a multi-task problem that I try to solve with a single neutral network. In general it works fine, but it seems like there is a room for improvement. The final loss to optimize looks like ...
0
votes
0answers
40 views

Multi-Model Learning | Text and Image | Mutually Differentiable Models | Is it possible?

Problem : Document classification of scanned financial documents using Text (OCR on the images) and Images. The documents are both structural (forms, tables), unstructured (letters, descriptions, ...
0
votes
1answer
262 views

Architecture for multivariate multi-time-series model where some features are TS specific and some features are global

I'm looking to build a time series model (using a TCN or a LSTM) with $N$ different series, each of which has $P$ series-specific features $\mathbf{X}$. My input array is of dimension $N \times t \...
0
votes
1answer
89 views

Why and how BERT can learn different attentions for each head?

https://towardsdatascience.com/deconstructing-bert-distilling-6-patterns-from-100-million-parameters-b49113672f77 I read the blog above. It visualizes that different color/head has different ...