Scribd
Upload
49 views

6 - Multi - Task - Learning

Multi-task learning uses a single neural network to perform multiple tasks simultaneously. It is useful when the tasks could benefit from shared lower-level features and sufficient similar data is available for each task. For example, an autonomous vehicle could use one network to detect pedestrians, cars, road signs, traffic lights, and cyclists instead of separate networks, since some early features can be shared between object types, improving overall performance. The network takes images with multiple labels as input and outputs predictions for each task. It is trained using a loss function that calculates error for each task without being influenced by unlabeled entries.

Uploaded by

Archit Mangrulkar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
49 views

6 - Multi - Task - Learning

Multi-task learning uses a single neural network to perform multiple tasks simultaneously. It is useful when the tasks could benefit from shared lower-level features and sufficient similar data is available for each task. For example, an autonomous vehicle could use one network to detect pedestrians, cars, road signs, traffic lights, and cyclists instead of separate networks, since some early features can be shared between object types, improving overall performance. The network takes images with multiple labels as input and outputs predictions for each task. It is trained using a loss function that calculates error for each task without being influenced by unlabeled entries.

Uploaded by

Archit Mangrulkar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Multi-task learning

Multi-task learning refers to having one neural network do simultaneously several tasks.

When to use multi-task learning


• Training on a set of tasks that could benefit from having shared lower-level features
• Usually: Amount of data you have for each task is quite similar
• Can train a big enough neural network to do well on all tasks

Example: Simplified autonomous vehicle


The vehicle has to detect simultaneously several things: pedestrians, cars, road signs, traffic lights, cyclists,
etc. We could have trained four separate neural networks, instead of train one to do four tasks. However,
in this case, the performance of the system is better when one neural network is trained to do four tasks
than training four separate neural networks since some of the earlier features in the neural network could
be shared between the different types of objects.

The input 𝑥 (𝑖) is the image with multiple labels


The output 𝑦 (𝑖) has 4 labels which are represents:
0 Pedestrians
(𝑖) 1 Cars
𝑦 = [ ]
1 Road signs - Stop
0 Traffic lights

| | | | 𝑌 = (4, 𝑚)
𝑌 = [𝑦 (1) (2) (3) (4) ]
𝑦 𝑦 𝑦
𝑌 = (4,1)
| | | |

Neural Network architecture Pedestrians

Cars

Road signs - Stop


To train this neural network, loss function is defined as follow: Traffic lights
𝑚 4
1 (𝑖) (𝑖) (𝑖) (𝑖)
− ∑ ∑ (𝑦𝑗 log (𝑦̂𝑗 ) + (1 − 𝑦𝑗 ) log (1 − 𝑦̂𝑗 ))
𝑚
𝑖=1 𝑗=1

Also, the cost can be compute such as it is not influenced by the fact that some entries are not labeled.
Example:
1 0 ? ?
0 1 ? 0
𝑌=[ ]
0 1 ? 1
? 0 1 0

You might also like