Autoencoders - EXPLAINED

Data around us, like images and documents, are very high dimensional. Autoencoders can learn a simpler representation of it. This representation can be used in many ways:
- fast data transfers across a network
- Self driving cars (Semantic Segmentation)
- Neural Inpainting: Completing sections of an image, or removing watermarks
- Latent Semantic Hashing: Clustering similar documents together.
And the list of applications goes on.

Clearly, Autoencoders can be useful. In this video, we are going to understand it's types and functions.

For more content, hit that SUBSCRIBE button, ring that bell.
Subscribe now for more awesome content: http://www.youtube.com/c/CodeEmporium?sub_confirmation=1
patreon: https://www.patreon.com/CodeEmporium
REFERENCES

[1] Autoencoders: https://www.deeplearningbook.org/contents/autoencoders.html
[2] Sparse autoencoder (last part): https://web.stanford.edu/class/cs294a/sparseAutoencoder.pdf
[3] Why are sparse encoders sparse?: https://www.quora.com/Why-are-sparse-autoencoders-sparse
[4] KL Divergence: https://en.wikipedia.org/wiki/Kullback%E2%80%93Leibler_divergence
[5] Semantic Hashing: https://www.cs.utoronto.ca/~rsalakhu/papers/semantic_final.pdf
[6] Variational Autoencoders: https://jaan.io/what-is-variational-autoencoder-vae-tutorial/
[7] Xander’s video on Variational AutoEncoders (Arxiv Insights): https://www.youtube.com/watch?v=9zKuYvjFFS8&t=1s&ab_channel=ArxivInsights

CLIPS
[1] Karol Majek’s Self driving car with RCNN: https://www.youtube.com/watch?v=OOT3UIXZztE&ab_channel=KarolMajek
[2] Auto encoder images: https://www.jeremyjordan.me/autoencoders/
[3] Semantic Segmentation with Autoencoders: https://github.com/arahusky/Tensorflow-Segmentation
[4] Neural Inpainting paper: https://arxiv.org/pdf/1611.09969.pdf
[5] GAN results: https://www.youtube.com/watch?time_continue=49&v=XOxxPcy5Gr4

#machinelearning #deeplearning #neuralnetwork #ai #datascience

Видео Autoencoders - EXPLAINED канала CodeEmporium