Reinforcement Learning with Augmented Data (Paper Explained)
This ONE SIMPLE TRICK can take a vanilla RL algorithm to achieve state-of-the-art. What is it? Simply augment your training data before feeding it to the learner! This can be dropped into any RL pipeline and promises big improvements across the board.
Abstract: Learning from visual observations is a fundamental yet challenging problem in reinforcement learning (RL). Although algorithmic advancements combined with convolutional neural networks have proved to be a recipe for success, current methods are still lacking on two fronts: (a) sample efficiency of learning and (b) generalization to new environments. To this end, we present RAD: Reinforcement Learning with Augmented Data, a simple plug-and-play module that can enhance any RL algorithm. We show that data augmentations such as random crop, color jitter, patch cutout, and random convolutions can enable simple RL algorithms to match and even outperform complex state-of-the-art methods across common benchmarks in terms of data-efficiency, generalization, and wall-clock speed. We find that data diversity alone can make agents focus on meaningful information from high-dimensional observations without any changes to the reinforcement learning method. On the DeepMind Control Suite, we show that RAD is state-of-the-art in terms of data-efficiency and performance across 15 environments. We further demonstrate that RAD can significantly improve the test-time generalization on several OpenAI ProcGen benchmarks. Finally, our customized data augmentation modules enable faster wall-clock speed compared to competing RL techniques. Our RAD module and training code are available at this https URL.
Authors: Michael Laskin, Kimin Lee, Adam Stooke, Lerrel Pinto, Pieter Abbeel, Aravind Srinivas
My thoughts on the let-the-young-get-infected argument.
https://medium.com/amnon-shashua/can-we-contain-covid-19-without-locking-down-the-economy-2a134a71873f
Abstract:
In this article, we present an analysis of a risk-based selective quarantine model where the population is divided into low and high-risk groups. The high-risk group is quarantined until the low-risk group achieves herd-immunity. We tackle the question of whether this model is safe, in the sense that the health system can contain the number of low-risk people that require severe ICU care (such as life support systems).
Authors: Shai Shalev-Shwartz, Amnon Shashua
Links:
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
BitChute: https://www.bitchute.com/channel/yannic-kilcher
Minds: https://www.minds.com/ykilcher
...
https://www.youtube.com/watch?v=XdpF9ZixIbI
#deeplearning #neuralinterpreter #ai
OUTLINE:
0:00 - Intro & Overview
3:00 - Model Overview
7:00 - Interpreter weights and function code
9:40 - Routing data to functions via neural type inference
14:55 - ModLin layers
18:25 - Experiments
21:35 - Interview Start
24:50 - General Model Structure
30:10 - Function code and signature
40:30 - Explaining Modulated Layers
49:50 - A closer look at weight sharing
58:30 - Experimental Results
Paper: https://arxiv.org/abs/2110.06399
Guests:
Nasim Rahaman: https://twitter.com/nasim_rahaman
Francesco Locatello: https://twitter.com/FrancescoLocat8
Waleed Gondal: https://twitter.com/Wallii_gondal
Abstract:
Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution. However, they are less capable of systematic generalization to data drawn from unseen but related distributions, a feat that is hypothesized to require compositional reasoning and reuse of knowledge. In this work, we present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules, which we call \emph{functions}. Inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. The proposed architecture can flexibly compose computation along width and depth, and lends itself well to capacity extension after training. To demonstrate the versatility of Neural Interpreters, we evaluate it in two distinct settings: image classification and visual abstract reasoning on Raven Progressive Matrices. In the former, we show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner. In the latter, we find that Neural Interpreters are competitive with respect to the state-of-the-art in terms of systematic generalization
Authors: Nasim Rahaman, Muhammad Waleed Gondal, Shruti Joshi, Peter Gehler, Yoshua Bengio, Francesco Locatello, Bernhard Schölkopf
Links:
TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://discord.gg/4H8xxDF
BitChute: https://www.bitchute.com/channel/yannic-kilcher
LinkedIn: https://www.linkedin.com/in/ykilcher
BiliBili: https://space.bilibili.com/2017636191
If you want to support me, the best thing to do is to share out the content :)
If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this):
SubscribeStar: https://www.subscribestar.com/yannickilcher
Patreon: https://www.patreon.com/yannickilcher
Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq
Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2
Litec
...
https://www.youtube.com/watch?v=w3knicSHx5s
#deeplearning #objectdetection #outliers
An interview with the authors of "Virtual Outlier Synthesis".
Watch the paper review video here: https://youtu.be/i-J4T3uLC9M
Outliers are data points that are highly unlikely to be seen in the training distribution, and therefore deep neural networks have troubles when dealing with them. Many approaches to detecting outliers at inference time have been proposed, but most of them show limited success. This paper presents Virtual Outlier Synthesis, which is a method that pairs synthetic outliers, forged in the latent space, with an energy-based regularization of the network at training time. The result is a deep network that can reliably detect outlier datapoints during inference with minimal overhead.
OUTLINE:
0:00 - Intro
2:20 - What was the motivation behind this paper?
5:30 - Why object detection?
11:05 - What's the connection to energy-based models?
12:15 - Is a Gaussian mixture model appropriate for high-dimensional data?
16:15 - What are the most important components of the method?
18:30 - What are the downstream effects of the regularizer?
22:00 - Are there severe trade-offs to outlier detection?
23:55 - Main experimental takeaways?
26:10 - Why do outlier detection in the last layer?
30:20 - What does it take to finish a research projects successfully?
Paper: https://arxiv.org/abs/2202.01197
Code: https://github.com/deeplearning-wisc/vos
Abstract:
Out-of-distribution (OOD) detection has received much attention lately due to its importance in the safe deployment of neural networks. One of the key challenges is that models lack supervision signals from unknown data, and as a result, can produce overconfident predictions on OOD data. Previous approaches rely on real outlier datasets for model regularization, which can be costly and sometimes infeasible to obtain in practice. In this paper, we present VOS, a novel framework for OOD detection by adaptively synthesizing virtual outliers that can meaningfully regularize the model's decision boundary during training. Specifically, VOS samples virtual outliers from the low-likelihood region of the class-conditional distribution estimated in the feature space. Alongside, we introduce a novel unknown-aware training objective, which contrastively shapes the uncertainty space between the ID data and synthesized outlier data. VOS achieves state-of-the-art performance on both object detection and image classification models, reducing the FPR95 by up to 7.87% compared to the previous best method. Code is available at this https URL.
Authors: Xuefeng Du, Zhaoning Wang, Mu Cai, Yixuan Li
Links:
Merch: http://store.ykilcher.com
TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter
...
https://www.youtube.com/watch?v=MgJ3JsE3Tqo
#imle #backpropagation #discrete
Backpropagation is the workhorse of deep learning, but unfortunately, it only works for continuous functions that are amenable to the chain rule of differentiation. Since discrete algorithms have no continuous derivative, deep networks with such algorithms as part of them cannot be effectively trained using backpropagation. This paper presents a method to incorporate a large class of algorithms, formulated as discrete exponential family distributions, into deep networks and derives gradient estimates that can easily be used in end-to-end backpropagation. This enables things like combinatorial optimizers to be part of a network's forward propagation natively.
OUTLINE:
0:00 - Intro & Overview
4:25 - Sponsor: Weights & Biases
6:15 - Problem Setup & Contributions
8:50 - Recap: Straight-Through Estimator
13:25 - Encoding the discrete problem as an inner product
19:45 - From algorithm to distribution
23:15 - Substituting the gradient
26:50 - Defining a target distribution
38:30 - Approximating marginals via perturb-and-MAP
45:10 - Entire algorithm recap
56:45 - Github Page & Example
Paper: https://arxiv.org/abs/2106.01798
Code (TF): https://github.com/nec-research/tf-imle
Code (Torch): https://github.com/uclnlp/torch-imle
Our Discord: https://discord.gg/4H8xxDF
Sponsor: Weights & Biases
https://wandb.com
Abstract:
Combining discrete probability distributions and combinatorial optimization problems with neural network components has numerous applications but poses several challenges. We propose Implicit Maximum Likelihood Estimation (I-MLE), a framework for end-to-end learning of models combining discrete exponential family distributions and differentiable neural components. I-MLE is widely applicable as it only requires the ability to compute the most probable states and does not rely on smooth relaxations. The framework encompasses several approaches such as perturbation-based implicit differentiation and recent methods to differentiate through black-box combinatorial solvers. We introduce a novel class of noise distributions for approximating marginals via perturb-and-MAP. Moreover, we show that I-MLE simplifies to maximum likelihood estimation when used in some recently studied learning settings that involve combinatorial solvers. Experiments on several datasets suggest that I-MLE is competitive with and often outperforms existing approaches which rely on problem-specific relaxations.
Authors: Mathias Niepert, Pasquale Minervini, Luca Franceschi
Links:
TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://discord.gg/4H8xxDF
BitChute: https://www.bitchute.com/channel/yannic-kilcher
LinkedIn: https://
...
https://www.youtube.com/watch?v=W2UT8NjUqrk
Facebook AI's new Text-To-Speech system is able to create 1 second of speech in as little as 500ms, making it real-time. What's even more impressive is the fact that this does not require a rack of GPUs, but runs on merely 4 CPUs.
OUTLINE:
0:00 - Intro
1:00 - Problem Formulation
3:20 - System Explanation
15:00 - Speeding up the computation
https://ai.facebook.com/blog/a-highly-efficient-real-time-text-to-speech-system-deployed-on-cpus/
Links:
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
BitChute: https://www.bitchute.com/channel/yannic-kilcher
Minds: https://www.minds.com/ykilcher
...
https://www.youtube.com/watch?v=XvDzZwoQFcU
Authors: David Ha, Jürgen Schmidhuber
Abstract:
We explore building generative neural network models of popular reinforcement learning environments. Our world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the environment. By using features extracted from the world model as inputs to an agent, we can train a very compact and simple policy that can solve the required task. We can even train our agent entirely inside of its own hallucinated dream generated by its world model, and transfer this policy back into the actual environment.
https://arxiv.org/abs/1803.10122
...
https://www.youtube.com/watch?v=dPsXxLyqpfs
#aiart #deeplearning #clip
Since the release of CLIP, the world of AI art has seen an unprecedented level of acceleration in what's possible to do. Whereas image generation had previously been mostly in the domain of scientists, now a community of professional artists, researchers, and amateurs are sending around colab notebooks and sharing their creations via social media. How did this happen? What is going on? And where do we go from here? Jack Morris and I attempt to answer some of these questions, following his blog post "The Weird and Wonderful World of AI Art" (linked below).
OUTLINE:
0:00 - Intro
2:30 - How does one get into AI art?
5:00 - Deep Dream & Style Transfer: the early days of art in deep learning
10:50 - The advent of GANs, ArtBreeder and TikTok
19:50 - Lacking control: Pre-CLIP art
22:40 - CLIP & DALL-E
30:20 - The shift to shared colabs
34:20 - Guided diffusion models
37:20 - Prompt engineering for art models
43:30 - GLIDE
47:00 - Video production & Disco Diffusion
48:40 - Economics, money, and NFTs
54:15 - What does the future hold for AI art?
Blog post: https://jxmo.notion.site/The-Weird-and-Wonderful-World-of-AI-Art-b9615a2e7278435b98380ff81ae1cf09
Jack's Blog: https://jxmo.io/
Links:
TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://discord.gg/4H8xxDF
BitChute: https://www.bitchute.com/channel/yannic-kilcher
LinkedIn: https://www.linkedin.com/in/ykilcher
BiliBili: https://space.bilibili.com/2017636191
If you want to support me, the best thing to do is to share out the content :)
If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this):
SubscribeStar: https://www.subscribestar.com/yannickilcher
Patreon: https://www.patreon.com/yannickilcher
Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq
Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2
Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m
Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n
...
https://www.youtube.com/watch?v=DdkenV-ZdJU
Abstract:
Deep reinforcement learning (RL) methods have driven impressive advances in artificial intelligence in recent years, exceeding human performance in domains ranging from Atari to Go to no-limit poker. This progress has drawn the attention of cognitive scientists interested in understanding human learning. However, the concern has been raised that deep RL may be too sample-inefficient – that is, it may simply be too slow – to provide a plausible model of how humans learn. In the present review, we counter this critique by describing recently developed techniques that allow deep RL to operate more nimbly, solving problems much more quickly than previous methods. Although these techniques were developed in an AI context, we propose that they may have rich implications for psychology and neuroscience. A key insight, arising from these AI methods, concerns the fundamental connection between fast RL and slower, more incremental forms of learning.
Authors: Matthew Botvinick, Sam Ritter, Jane X. Wang, Zeb Kurth-Nelson, Charles Blundell, Demis Hassabis
https://www.cell.com/trends/cognitive-sciences/fulltext/S1364-6613(19)30061-0
...
https://www.youtube.com/watch?v=_N_nFzMtWkA