Cleaning tedious data is not simple as it seems
https://www.youtube.com/watch?v=MiiWzJE0fEA
https://www.youtube.com/watch?v=MiiWzJE0fEA
YouTube
"Probabilistic scripts for automating common-sense tasks" by Alexander Lew
As engineers, we love automating tedious tasks. But when those tasks require common-sense reasoning, automation can be difficult. Consider, for example, cleaning a messy dataset-full of typos, NULL values, numbers in the wrong units, and other problems. People…
A Roundup Review of the Best Deep Learning Books
https://blog.soshace.com/en/python/a-roundup-review-of-the-best-deep-learning-books/
https://blog.soshace.com/en/python/a-roundup-review-of-the-best-deep-learning-books/
Soshace
A Roundup Review of the Best Deep Learning Books - Soshace
If you’re interested in starting out or expanding your knowledge in neural networks and deep learning, then this roundup review of the best deep learning books might be a good starting point.
Here's lexfridman conversation with Leonard Susskind, a professor of theoretical physics at Stanford, one of the fathers of string theory, and one of the greatest physicists of our time, both as a researcher and an educator : https://lnkd.in/eP9pR4d https://t.iss.one/ArtificialIntelligenceArticles
Attention? Attention!
Blog by Lilian Weng : https://lilianweng.github.io/lil-log/2018/06/24/attention-attention.html
#machinelearning #neuralnetwork #transformers
Blog by Lilian Weng : https://lilianweng.github.io/lil-log/2018/06/24/attention-attention.html
#machinelearning #neuralnetwork #transformers
Lil'Log
Attention Attention
InterpretML: A Unified Framework for Machine Learning Interpretability. https://arxiv.org/abs/1909.09223
Robot Sound Interpretation: Combining Sight and Sound in Learning-Based Control. https://arxiv.org/abs/1909.09172
DeepView: Visualizing the behavior of deep neural networks in a part of the data space. https://arxiv.org/abs/1909.09154
Timage -- A Robust Time Series Classification Pipeline. https://arxiv.org/abs/1909.09149
HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models
Human evaluation for generative models have been ad-hoc.
They propose a standard human benchmark for generative realism that is grounded in psychophysics research in perception.
https://arxiv.org/abs/1904.01121
https://hype.stanford.edu/
Human evaluation for generative models have been ad-hoc.
They propose a standard human benchmark for generative realism that is grounded in psychophysics research in perception.
https://arxiv.org/abs/1904.01121
https://hype.stanford.edu/
arXiv.org
HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models
Generative models often use human evaluations to measure the perceived quality of their outputs. Automated metrics are noisy indirect proxies, because they rely on heuristics or pretrained...
BagNet: Berkeley Analog Generator with Layout Optimizer Boosted with Deep Neural Networks
Hakhamaneshi et al.: https://arxiv.org/abs/1907.10515
#SignalProcessing #MachineLearning #NeuralComputing
Hakhamaneshi et al.: https://arxiv.org/abs/1907.10515
#SignalProcessing #MachineLearning #NeuralComputing
Equilibrium Propagation: Bridging the Gap between Energy-Based Models and Backpropagation
https://www.frontiersin.org/articles/10.3389/fncom.2017.00024/full
https://www.frontiersin.org/articles/10.3389/fncom.2017.00024/full
Frontiers
Equilibrium Propagation: Bridging the Gap between Energy-Based Models and Backpropagation
We introduce Equilibrium Propagation, a learning framework for energy-based models. It involves only one kind of neural computation, performed in both the first phase (when the prediction is made) and the second phase of training (after the target or prediction…
Intelligent artificial agents learning to play 'hide and seek'
https://www.profillic.com/paper/arxiv:1909.07528
https://www.profillic.com/paper/arxiv:1909.07528
Profillic
Profillic: AI models, code & research to supercharge your projects
Explore state-of-the-art in machine learning, AI, and robotics research. Browse models, source code, papers by topics and authors. Connect with researchers and engineers working on related problems in machine learning, deep learning, natural language processing…
rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch
Blog by Adam Stookei : https://bair.berkeley.edu/blog/2019/09/24/rlpyt/
#DeepLearning #ReinforcementLearning #PyTorch
Blog by Adam Stookei : https://bair.berkeley.edu/blog/2019/09/24/rlpyt/
#DeepLearning #ReinforcementLearning #PyTorch
The Berkeley Artificial Intelligence Research Blog
rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch
The BAIR Blog
Deep Dynamics Models for Learning Dexterous Manipulation
Nagabandi et al.: https://arxiv.org/abs/1909.11652
#Robotics #MachineLearning #ReinforcementLearning
Nagabandi et al.: https://arxiv.org/abs/1909.11652
#Robotics #MachineLearning #ReinforcementLearning
arXiv.org
Deep Dynamics Models for Learning Dexterous Manipulation
Dexterous multi-fingered hands can provide robots with the ability to flexibly perform a wide range of manipulation skills. However, many of the more complex behaviors are also notoriously...
Identifying and eliminating bugs in learned predictive models
https://deepmind.com/blog/article/robust-and-verified-ai
https://deepmind.com/blog/article/robust-and-verified-ai
Deepmind
Towards Robust and Verified AI: Specification Testing, Robust Training, and Formal Verification
One in a series of posts explaining the theories underpinning our research. Bugs and software have gone hand in hand since the beginning of computer programming. Over time, software developers have established a set of best practices for testing and debugging…
AI solution about RealEstate in Singapore
They built on open-source geospatial features and were able to predict Singapore real estate prices with 87% accuracy (i.e., within an error margin of S$100).
They used a) OpenStreetMap (https://download.geofabrik.de/asia/malaysia-singapore-brunei.html)
b) Geomancer for geospatial features (https://stories.thinkingmachin.es/geomancer/)
Link: https://download.geofabrik.de/asia/malaysia-singapore-brunei.html
They built on open-source geospatial features and were able to predict Singapore real estate prices with 87% accuracy (i.e., within an error margin of S$100).
They used a) OpenStreetMap (https://download.geofabrik.de/asia/malaysia-singapore-brunei.html)
b) Geomancer for geospatial features (https://stories.thinkingmachin.es/geomancer/)
Link: https://download.geofabrik.de/asia/malaysia-singapore-brunei.html
stories.thinkingmachin.es
Introducing Geomancer: an open-source library for geospatial feature engineering
Tired of doing all of your geospatial feature engineering from scratch? Don’t fret; we’ve got a magical tool for you!
Extreme Language Model Compression with Optimal Subwords and Shared Projections
Zhao et al.: https://arxiv.org/abs/1909.11687
#neuralnetwork #bert #nlp
Zhao et al.: https://arxiv.org/abs/1909.11687
#neuralnetwork #bert #nlp
arXiv.org
Extremely Small BERT Models from Mixed-Vocabulary Training
Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint. A large fraction of this footprint comes from...
Mathematical Reasoning in Latent Space
Lee et al.: https://arxiv.org/pdf/1909.11851v1.pdf
#Mathematics #Reasoning #LatentSpace
Lee et al.: https://arxiv.org/pdf/1909.11851v1.pdf
#Mathematics #Reasoning #LatentSpace
Learning Pixel Representations for Generic Segmentation. https://arxiv.org/abs/1909.11735