There is a Luka — asisstent to pick places nearby. Works only in SF, but it looks promicing: http://luka.ai
replika.com
Always here to listen and talk. Always on your side. Join the millions growing with their AI friends now!
Paper about recent AlphaGo solution.
https://storage.googleapis.com/deepmind-data/assets/papers/deepmind-mastering-go.pdf
https://storage.googleapis.com/deepmind-data/assets/papers/deepmind-mastering-go.pdf
A very important picture from a recent LeCun CVPR. Important for those, who want to study QA / Dialogue systems.
Deep residual networks from Microsoft Research Asia (MSRA).
https://github.com/KaimingHe/deep-residual-networks
https://github.com/KaimingHe/deep-residual-networks
GitHub
GitHub - KaimingHe/deep-residual-networks: Deep Residual Learning for Image Recognition
Deep Residual Learning for Image Recognition . Contribute to KaimingHe/deep-residual-networks development by creating an account on GitHub.
Deep learning methods are able to automatically discover better representations of the data to improve the performance of the classifiers. However, in computer vision tasks, such as the gender recognition problem, sometimes it is difficult to directly learn from the entire image. In this work we propose a new model called Local Deep Neural Network (Local-DNN), which is based on two key concepts: local features and deep architectures. The model learns from small overlapping regions in the visual field using discriminative feed-forward networks with several layers. We evaluate our approach on two well-known gender benchmarks, showing that our Local-DNN outperforms other deep learning methods also evaluated and obtains state-of-the-art results in both benchmarks.
http://www.sciencedirect.com/science/article/pii/S0167865515004018
http://www.sciencedirect.com/science/article/pii/S0167865515004018
New Deep Mind team breakthrough — system is able to navigate through Doom
https://www.newscientist.com/article/2076552-google-deepmind-ai-navigates-a-doom-like-3d-maze-just-by-looking/
https://www.newscientist.com/article/2076552-google-deepmind-ai-navigates-a-doom-like-3d-maze-just-by-looking/
New Scientist
Google DeepMind AI navigates a <em>Doom</em>-like 3D maze just by looking
The artificial intelligence firm has come up with a computer learning technique that requires less processing power, allowing it to reach new heights
NVidia Released cuDNN v.4.0.
Though we do not recommend to use it right away, especially on macs, since running bleeding edge can result in great pain for the developer. But be aware, that cuDNN 4.0 is now awailable
Though we do not recommend to use it right away, especially on macs, since running bleeding edge can result in great pain for the developer. But be aware, that cuDNN 4.0 is now awailable