1649280316_maxresdefault.jpg
73
04:23

Item-to-item recommendation and sequential recommendation

Learn about item-to-item recommendation and sequential recommendation, two popular retrieval models, for TensorFlow Recommenders with Developer Advocate Wei Wei. Resources: Item-to-item recommendation → https://goo.gle/3x6vGuU Recommending movies: retrieval using a sequential model → https://goo.gle/3DGhn1a Recurrent Neural Networks with Top-k Gains for Session-based Recommendations → https://goo.gle/36V48hi Chapters: 0:00 – Introduction 0:24 – item-to-item recommendation 1:14 – Sequential […]
1640456924_maxresdefault.jpg
256
04:12

Two Minute Papers: Visually Indicated Sounds | Two Minute Papers #79

The Scholarly Store is available here: https://shop.spreadshirt.net/TwoMinutePapers Using the power of deep learning, it is now possible to create a technique that looks at a silent video and synthesize appropriate sound effects for it. The usage is at the moment, limited to hitting these objects with a drumstick. Note: The authors seem to lean on […]
1639568037_maxresdefault.jpg
631
02:33

Two Minute Papers: AI Learns Visual Common Sense With New Dataset | Two Minute Papers #169

The paper “The “something something” video database for learning and evaluating visual common sense” is available here: https://arxiv.org/abs/1706.04261 Source for the video results: https://medium.com/@raghavgoyal14/7383596f58df Recommended for you: Recurrent Neural Network Writes Sentences About Images – https://www.youtube.com/watch?v=e-WB4lfg30M Two Minute Papers Merch: US: http://twominutepapers.com/ EU/Worldwide: https://shop.spreadshirt.net/TwoMinutePapers/ WE WOULD LIKE TO THANK OUR GENEROUS PATREON SUPPORTERS WHO MAKE […]
1639502915_maxresdefault.jpg
466
03:14

Two Minute Papers: Hallucinating Images With Deep Learning | Two Minute Papers #74

During our journeys in deep learning, we have seen techniques that can summarize photographs in entire sentences that actually make sense. This time, we are going to turn this process around and ask a deep learning system to “hallucinate”, i.e., generate images according to sentences that we add as an input. The results are nothing […]
1637283969_maxresdefault.jpg
10
04:56

CoRL 2020, Spotlight Talk 159: Action-Conditional Recurrent Kalman Networks For Forward and Inver…

“**Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning** Vaisakh Shaj (Karlsruhe Institute Of Technology)*; Philipp Becker (Karlsruhe Institute of Technology (KIT)); Dieter Büchler (MPI for Intelligent Systems Tübingen); Harit Pandya (University of Lincoln); Niels van Duijkeren (Bosch Corporate Research); C. James Taylor (Lancaster University); Marc Hanheide (University of Lincoln); Gerhard Neumann (KIT) Publication: […]
1636811220_maxresdefault.jpg
1.38K
04:02

Two Minute Papers: 10 Even Cooler Deep Learning Applications | Two Minute Papers #59

For the third time, we present another round of incredible deep learning applications! ___________________ 1. Geolocation – http://arxiv.org/abs/1602.05314 2. Super-resolution – http://arxiv.org/pdf/1511.04491v1.pdf 3. Neural Network visualizer – http://experiments.mostafa.io/public/ffbpann/ 4. Recurrent neural network for sentence completion: http://www.cs.toronto.edu/~ilya/fourth.cgi 5. Human-in-the-loop and Doctor-in-the-loop: http://link.springer.com/article/10.1007/s40708-016-0036-4 6. Emoji suggestions for images – https://emojini.curalate.com/ 7. MNIST handwritten numbers in HD – […]
1636346952_maxresdefault.jpg
0

DeepMind’s AI Learns Superhuman Relational Reasoning | Two Minute Papers #168

The paper “A simple neural network module for relational reasoning” is available here: https://arxiv.org/abs/1706.01427 Details on our Patreon page: https://www.patreon.com/TwoMinutePapers More on Long Short-Term Memory: Recurrent Neural Network Writes Music and Shakespeare Novels – https://www.youtube.com/watch?v=Jkkjy7dVdaY Recurrent Neural Network Writes Sentences About Images – https://www.youtube.com/watch?v=e-WB4lfg30M Two Minute Papers Merch: US: http://twominutepapers.com/ EU/Worldwide: https://shop.spreadshirt.net/TwoMinutePapers/ WE WOULD LIKE […]
1636343284_maxresdefault.jpg
2.67K
03:50

What is an Autoencoder? | Two Minute Papers #86

Autoencoders are neural networks that are capable of creating sparse representations of the input data and can therefore be used for image compression. There are denoising autoencoders that after learning these sparse representations, can be presented with noisy images. What is even better is a variant that is called the variational autoencoder that not only […]
1636328480_hqdefault.jpg
1.54K
03:58

10 More Cool Deep Learning Applications | Two Minute Papers #52

In this episode, we present another round of incredible deep learning applications! _________________________ 1. Colorization – http://tinyclouds.org/colorize/ 2. RNN Music on Bob Sturm’s YouTube channel – https://www.youtube.com/watch?v=RaO4HpM07hE 3. Flow Machines by Sony – https://www.youtube.com/watch?v=buXqNqBFd6E 4. RNN Passwords – https://github.com/gehaxelt/RNN-Passwords 5. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding – http://arxiv.org/abs/1510.00149 […]
1636251316_maxresdefault.jpg
0

Image Synthesis From Text With Deep Learning | Two Minute Papers #116

The paper “StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks” is available here: https://arxiv.org/abs/1612.03242 Source code for this project is also available here: https://github.com/hanzhanggit/StackGAN We have a Patreon post on the improvements you can expect from Two Minute Papers in 2017. Lots of goodies behind the link, have a look! https://www.patreon.com/posts/7607896 Our […]
1636166398_maxresdefault.jpg
0

AI Learns To Create User Interfaces (pix2code) | Two Minute Papers #161

The paper “pix2code: Generating Code from a Graphical User Interface Screenshot” is available here: https://arxiv.org/abs/1705.07962 https://github.com/tonybeltramelli/pix2code Recommended for you: Recurrent Neural Network Writes Music and Shakespeare Novels – Two Minute Papers Merch: US: http://twominutepapers.com/ EU/Worldwide: https://shop.spreadshirt.net/TwoMinutePapers/ WE WOULD LIKE TO THANK OUR GENEROUS PATREON SUPPORTERS WHO MAKE TWO MINUTE PAPERS POSSIBLE: Andrew Melnychuk, Christian Lawson, […]
1635444394_maxresdefault.jpg
2
01:11:42

Recitation 6: RNN Basics

00:00 Introduction 00:07:06 RNN Unrolled – through time/steps 00:15:54 Text Vector Representation 00:21:38 Prediction Example 00:31:30 Generation Example 00:37:13 Problems Training 00:52:46 Language Model – Code Walkthrough YouTube Source for this AI Video
1635411074_maxresdefault.jpg
0
10:58

Recitation 6 | RNN p1

Carnegie Mellon University Course: 11-785, Intro to Deep Learning Offering: Fall 2020 For more information, please visit: https://deeplearning.cs.cmu.edu/ YouTube Source for this AI Video
1635385399_maxresdefault.jpg
4
01:22:08

Lecture 14: Stability and Memory, LSTMs

00:00 Recap 00:04:50 MLP vs RNN 00:16:16 Linear Systems 00:25:01 Linear Recursions 00:48:05 Stability Analysis 01:02:10 Exploding or Vanishing Gradients YouTube Source for this AI Video
1635189363_maxresdefault.jpg
6
01:24:05

Lecture 13: Recurrent Networks

00:00 Introduction 00:14:55 Finite Response Model 00:23:00 Infinite Response System 00:30:00 NARX Network 00:34:30 Jordan Network 00:35:50 Elman Network 00:43:00 State Space Model 00:51:30 Recurrent Neural Network 00:59:10 Variants 01:04:30 Training the RNN 01:10:50 Backpropagation through RNN YouTube Source for this AI Video
1635095537_maxresdefault.jpg
3
39:33

Learning Long-Time Dependencies with RNNs w/ Konstantin Rusch – #484

Today we conclude our 2021 ICLR coverage joined by Konstantin Rusch, a Ph.D. Student at ETH Zurich. In our conversation with Konstantin, we explore his recent papers, titled coRNN and uniCORNN respectively, which focus on a novel architecture of recurrent neural networks for learning long-time dependencies. We explore the inspiration he drew from neuroscience when […]