Tell us about yourself ...
Full BioTell us about yourself
New deep-learning based AI software could pave the way for artificial intelligence to work without internet
1161 days ago
Understanding data breaches
1161 days ago
Tech companies dangle fat packages at campuses for niche roles
1163 days ago
Supercomputing speeds up deep learning training
1163 days ago
Researchers built an invisible backdoor to hack AI's decisions
1244 days ago
Zomato chatting with a customer about lost food and love is a lesson for all bots
22332 views
Tech companies dangle fat packages at campuses for niche roles
22113 views
Here is why India is likely to lose the AI race
21792 views
Here is why India is likely to lose the AI race
21792 views
Chatbot helps Tata Capital increase lead generation by 600 percent
16347 views
Google's Tensor2Tensor makes it easier to conduct deep learning experiments
Google's brain team is open sourcing Tensor2Tensor, a new deep learning library designed to help researchers replicate results from recent papers in the field and push the boundaries of what's possible by trying new combinations of models, datasets and other parameters. The sheer number of variables in AI research combined with the fast pace of new developments makes it difficult for experiments run in two distinct settings to match. This is a pain for researchers and a drag on research progress.
The Tensor2Tensor library makes it easier to maintain best practices while conducting AI research. It comes equipped with key ingredients including hyperparameters, data-sets, model architectures and learning rate decay schemes.
The best part is that any of these components can be swapped in and out in a modular fashion without completely destroying everything. From a training perspective, this means that with Tensor2Tensor you can bring in new models and data sets at any time - a much simpler process than would ordinarily be possible.
Google isn't alone in its pursuits to help make research more reproducible outside the lab. Facebook recently open sourced ParlAI, its tool to facilitate dialog research that comes prepackaged with commonly used datasets.
Similarly, Google's Tensor2Tensor comes with models from recent Google research projects like "Attention Is All You Need" and "One Model to Learn Them All." Everything is available now on Github so you can start training your own deep learning-powered tools.