TGViewer
Channel Public Channel
AI, Python, Cognitive Neuroscience

AI, Python, Cognitive Neuroscience

@ai_python_en

Open in Telegram
Subscribers
3.45K
Photos
1.1K
Videos
47
Links
891

Showing posts older than #1925 · Back to latest

Older Posts 20 shown
Post #1921 5.71K
Github has just launched a new NLP/information retrieval challenge: CodeSearchNet challenge. The goal of code search is to retrieve relevant code given natural language. Along with this, they released a huge dataset with: - 6m functions across 6 programming languages (Go, Java, Python etc) - 2m of those 6m functions have associated documentation (docstrings, JavaDoc etc) - And some metadata (line number and more). They also included some baseline models (e.g. BERT-like self-attention model) to help people get started with the challenge. Check it out! #deeplearning #machinelearning


📝 Article: https://lnkd.in/dezzhs9
🔤 Code: https://lnkd.in/dXhRqpE


✴️ @AI_PYTHON_EN
Post #1920 970
Self-Paced Learning:
- supervised method from 2010 #NIPS
- idea: start learning with the easiest samples first and only then learn the difficult ones
- distinct from curriculum learning, where samples are pre-classified to easy/hard: we need to decide the order on our own
sample in a latent model (outliers will be the hardest)
- a better measure (!): how good are the initial predictions for the sample (samples far away from the decision boundary are the easiest).

- for #classification, samples are only easy in context of other samples!
- the set of easy samples is iteratively enlarged
- results: outperforms CCCP in #DNA Motif Finding, handwritten digit recognition and others problems
- link: https://papers.nips.cc/paper/3923-self-paced-learning-for-latent-variable-models
papers.nips.cc Self-Paced Learning for Latent Variable Models Electronic Proceedings of Neural Information Processing Systems
Post #1917 937
Google researchers just released #ALBERT , that has beaten all models across various benchmarks.

Also, did you know that most NLP models achieves performance that outpaces average human performance?
——————————————————
ALBERT uses parameter reduction techniques to lower memory consumption and increase the training speed of BERT

1. They topped GLUE ( https://lnkd.in/dkWNRVk ) — 92.2%

2. SQuAD (https://lnkd.in/d_Xrba8 ) leaderboards. — 89.4%

3. RACE - they came third with their ensemble model (https://lnkd.in/d2yWbtC ) — 89.4%
——————————————————
Paper at openreview: https://lnkd.in/dzRvWYS
#deeplearning #machinelearning #NLU #NLG #artificiallintelligence #ai
Post #1915 5.18K
PyTorch implementations of deep reinforcement learning algorithms and environments

GitHub, by Petros Christodoulou : https://lnkd.in/eRZCQ-d

#pytorch #reinforcementlearning #deeplearning
GitHub GitHub - p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch: PyTorch implementations of deep reinforcement learning algorithms… PyTorch implementations of deep reinforcement learning algorithms and environments - GitHub - p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch: PyTorch implementations of deep reinforce...
Post #1914 1.07K
#AI for Mammography and Digital Breast Tomosynthesis: Current Concepts and Future Perspectives​. Krzysztof et al explain in the newest Radiology article below.
http://bit.ly/2kULbDz
pubs.rsna.org Artificial Intelligence for Mammography and Digital Breast Tomosynthesis: Current Concepts and Future Perspectives | Radiology Although computer-aided diagnosis (CAD) is widely used in mammography, conventional CAD programs that use prompts to indicate potential cancers on the mammograms have not led to an improvement in d...
Post #1913 989
Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis
pdf: https://arxiv.org/pdf/1909.12224.pdf
abs: https://arxiv.org/abs/1909.12224
project page: https://svip-lab.github.io/project/impersonator.html
github: https://github.com/svip-lab/imper
arXiv.org Liquid Warping GAN: A Unified Framework for Human Motion... We tackle the human motion imitation, appearance transfer, and novel view synthesis within a unified framework, which means that the model once being trained can be used to handle all these tasks....
Post #1910 1.2K
AI, Python, Cognitive Neuroscience 2_5203986206391534542.pdf
If you just published a paper let us inform other members.
@ai_python_en
Post #1909 5.89K
2_5203986206391534542.pdf1.5 MB
Sarbazi, M., Sadeghzadeh, M., & Mir Abedini, S. J. (2019). Improving resource allocation in software-defined networks using clustering. Cluster Computing.
doi:10.1007/s10586-019-02985-3

❇️ @AI_Python_EN
Post #1905 1.09K
​​FSGAN: Subject Agnostic Face Swapping and Reenactment

New paper on #DeepFakes creation

YouTube demo:
https://www.youtube.com/watch?v=duo-tHbSdMk
Link:
https://nirkin.com/fsgan/
ArXiV:
https://arxiv.org/pdf/1908.05932.pdf

#FaceSwap #DL #Video #CV
YouTube New Face Swapping AI Creates Amazing DeepFakes! 📝 The paper "FSGAN: Subject Agnostic Face Swapping and Reenactment" is available here: https://nirkin.com/fsgan/ ❤️ Pick up cool perks on our Patreon page: https://www.patreon.com/TwoMinutePapers 🙏 We would like to thank our generous Patreon supporters…
Post #1903 1.04K
​​Light regression analysis of some Microsoft employees salary distrubution

How basic knowledge of regression and couple of graphs can make an information look much better and clear.

Link: https://onezero.medium.com/leak-of-microsoft-salaries-shows-fight-for-higher-compensation-3010c589b41e

#regression #simple #salary #infographic
Medium Leak of Microsoft Salaries Shows Fight for Higher Compensation The numbers range from $40,000 to $320,000 and reveal key details about how pay works at big tech companies
Post #1902 963
Depth Hints are complementary depth suggestions which improve monocular depth estimation algorithms trained from stereo pairs

code:
https://github.com/nianticlabs/depth-hints

paper:
https://arxiv.org/abs/1909.09051

dataset :
https://lmb.informatik.uni-freiburg.de/resources/datasets/SceneFlowDatasets.en.html
GitHub GitHub - nianticlabs/depth-hints: [ICCV 2019] Depth Hints are complementary depth suggestions which improve monocular depth estimation… [ICCV 2019] Depth Hints are complementary depth suggestions which improve monocular depth estimation algorithms trained from stereo pairs - nianticlabs/depth-hints
Post #1901 926
Neural networks in NLP are vulnerable to adversarially crafted inputs.

We show that they can be trained to become certifiably robust against input perturbations such as typos and synonym substitution in text classification:

https://arxiv.org/abs/1909.01492
arXiv.org Achieving Verified Robustness to Symbol Substitutions via Interval... Neural networks are part of many contemporary NLP systems, yet their empirical successes come at the price of vulnerability to adversarial attacks. Previous work has used adversarial training and...
Older posts →
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →