It's common for neural networks to include data normalization such as BatchNorm or GroupNorm. This paper extends the normalization to also include the weights of the network. This surprisingly simple change leads to a boost in performance and - combined with GroupNorm - new state-of-the-art results.
Abstract: In this paper, we propose Weight Standardization (WS) to accelerate deep network training. WS is targeted at the micro-batch training setting where each GPU typically has only 1-2 images for training. The micro-batch training setting is hard because small batch sizes are not enough for training networks with Batch Normalization (BN), while other normalization methods that do not rely on batch knowledge still have difficulty matching the performances of BN in large-batch training. Our WS ends this problem because when used with Group Normalization and trained with 1 image/GPU, WS is able to match or outperform the performances of BN trained with large batch sizes with only 2 more lines of code. In micro-batch training, WS significantly outperforms other normalization methods. WS achieves these superior results by standardizing the weights in the convolutional layers, which we show is able to smooth the loss landscape by reducing the Lipschitz constants of the loss and the gradients. The effectiveness of WS is verified on many tasks, including image classification, object detection, instance segmentation, video recognition, semantic segmentation, and point cloud recognition. The code is available here: this https URL.
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
This paper shows that the original BERT model, if trained correctly, can outperform all of the improvements that have been proposed lately, raising questions about the necessity and reasoning behind these.
Abstract:
Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different sizes, and, as we will show, hyperparameter choices have significant impact on the final results. We present a replication study of BERT pretraining (Devlin et al., 2019) that carefully measures the impact of many key hyperparameters and training data size. We find that BERT was significantly undertrained, and can match or exceed the performance of every model published after it. Our best model achieves state-of-the-art results on GLUE, RACE and SQuAD. These results highlight the importance of previously overlooked design choices, and raise questions about the source of recently reported improvements. We release our models and code.
Authors: Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov
https://arxiv.org/abs/1907.11692
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Minds: https://www.minds.com/ykilcher
BitChute: https://www.bitchute.com/channel/10a5ui845DOJ/
...
https://www.youtube.com/watch?v=-MCYbmU9kfg
#ai #research #machinelearning
Neural Architecture Search is typically very slow and resource-intensive. A meta-controller has to train many hundreds or thousands of different models to find a suitable building plan. This paper proposes to use statistics of the Jacobian around data points to estimate the performance of proposed architectures at initialization. This method does not require training and speeds up NAS by orders of magnitude.
OUTLINE:
0:00 - Intro & Overview
0:50 - Neural Architecture Search
4:15 - Controller-based NAS
7:35 - Architecture Search Without Training
9:30 - Linearization Around Datapoints
14:10 - Linearization Statistics
19:00 - NAS-201 Benchmark
20:15 - Experiments
34:15 - Conclusion & Comments
Paper: https://arxiv.org/abs/2006.04647
Code: https://github.com/BayesWatch/nas-without-training
Abstract:
The time and effort involved in hand-designing deep neural networks is immense. This has prompted the development of Neural Architecture Search (NAS) techniques to automate this design. However, NAS algorithms tend to be extremely slow and expensive; they need to train vast numbers of candidate networks to inform the search process. This could be remedied if we could infer a network's trained accuracy from its initial state. In this work, we examine how the linear maps induced by data points correlate for untrained network architectures in the NAS-Bench-201 search space, and motivate how this can be used to give a measure of modelling flexibility which is highly indicative of a network's trained performance. We incorporate this measure into a simple algorithm that allows us to search for powerful networks without any training in a matter of seconds on a single GPU. Code to reproduce our experiments is available at this https URL.
Authors: Joseph Mellor, Jack Turner, Amos Storkey, Elliot J. Crowley
Links:
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
Minds: https://www.minds.com/ykilcher
Parler: https://parler.com/profile/YannicKilcher
LinkedIn: https://www.linkedin.com/in/yannic-kilcher-488534136/
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 (preferred to Patreon): 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=a6v92P0EbJc
OUTLINE:
0:00 - Intro
0:30 - Google RL creates next-gen TPUs
2:15 - Facebook launches NetHack challenge
3:50 - OpenAI mitigates bias by fine-tuning
9:05 - Google AI releases browseable reconstruction of human cortex
9:50 - GPT-J 6B Transformer in JAX
12:00 - Tensorflow launches Forum
13:50 - Text style transfer from a single word
15:45 - ALiEn artificial life simulator
My Video on Chip Placement: https://youtu.be/PDRtyrVskMU
References:
RL creates next-gen TPUs
https://www.nature.com/articles/s41586-021-03544-w
https://www.youtube.com/watch?v=PDRtyrVskMU
Facebook launches NetHack challenge
https://ai.facebook.com/blog/launching-the-nethack-challenge-at-neurips-2021/
Mitigating bias by fine-tuning
https://openai.com/blog/improving-language-model-behavior/?s=09
Human Cortex 3D Reconstruction
https://ai.googleblog.com/2021/06/a-browsable-petascale-reconstruction-of.html
GPT-J: An open-source 6B transformer
https://arankomatsuzaki.wordpress.com/2021/06/04/gpt-j/
https://6b.eleuther.ai/
https://github.com/kingoflolz/mesh-transformer-jax/#gpt-j-6b
Tensorflow launches "Forum"
https://discuss.tensorflow.org/
Text style transfer from single word
https://ai.facebook.com/blog/ai-can-now-emulate-text-style-in-images-in-one-shot-using-just-a-single-word/
ALiEn Life Simulator
https://github.com/chrxh/alien
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
Minds: https://www.minds.com/ykilcher
Parler: https://parler.com/profile/YannicKilcher
LinkedIn: https://www.linkedin.com/in/yannic-kilcher-488534136/
BiliBili: https://space.bilibili.com/1824646584
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=Ihg4XDWOy68
#mlnews #kilcher #withtheauthors
Many of you have given me feedback on what you did and didn't like about the recent "with the authors" videos. Here's the result of that feedback and an outlook into the future.
Merch: http://store.ykilcher.com
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=cO1nSnsH_CQ
The cross-entropy loss has been the default in deep learning for the last few years for supervised learning. This paper proposes a new loss, the supervised contrastive loss, and uses it to pre-train the network in a supervised fashion. The resulting model, when fine-tuned to ImageNet, achieves new state-of-the-art.
https://arxiv.org/abs/2004.11362
Abstract:
Cross entropy is the most widely used loss function for supervised training of image classification models. In this paper, we propose a novel training methodology that consistently outperforms cross entropy on supervised learning tasks across different architectures and data augmentations. We modify the batch contrastive loss, which has recently been shown to be very effective at learning powerful representations in the self-supervised setting. We are thus able to leverage label information more effectively than cross entropy. Clusters of points belonging to the same class are pulled together in embedding space, while simultaneously pushing apart clusters of samples from different classes. In addition to this, we leverage key ingredients such as large batch sizes and normalized embeddings, which have been shown to benefit self-supervised learning. On both ResNet-50 and ResNet-200, we outperform cross entropy by over 1%, setting a new state of the art number of 78.8% among methods that use AutoAugment data augmentation. The loss also shows clear benefits for robustness to natural corruptions on standard benchmarks on both calibration and accuracy. Compared to cross entropy, our supervised contrastive loss is more stable to hyperparameter settings such as optimizers or data augmentations.
Authors: Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, Dilip Krishnan
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=MpdbFLXOOIw
#cybercrime #chatgpt #security
An interview with Sergey Shykevich, Threat Intelligence Group Manager at Check Point, about how models like ChatGPT have impacted the realm of cyber crime.
https://threatmap.checkpoint.com/
Links:
Homepage: https://ykilcher.com
Merch: https://ykilcher.com/merch
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://ykilcher.com/discord
LinkedIn: https://www.linkedin.com/in/ykilcher
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=10nEx2-8J0M
https://arxiv.org/abs/1810.04805
Abstract:
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT representations can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications.
BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE benchmark to 80.4% (7.6% absolute improvement), MultiNLI accuracy to 86.7 (5.6% absolute improvement) and the SQuAD v1.1 question answering Test F1 to 93.2 (1.5% absolute improvement), outperforming human performance by 2.0%.
Authors:
Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova
...
https://www.youtube.com/watch?v=-9evrZnBorM