
Director of Engineering @Integrated_IP #AI #MachineLearning #DeepLearning #DataScience
Bellingham, WA
Joined July 2019
- Tweets9
- Following520
- Followers64
- Likes188
Austin Corotan retweeted
More businesses, organizations, and startups are talking about machine learning and what it means for business than just about any other technological advance. How do you deploy ML initiatives, then? #DataScience #MachineLearning hubs.ly/H0kp4BH0
Austin Corotan retweeted
Facebook AI researchers and engineers have developed a new method for using deep learning and weakly supervised training to predict road networks from commercially available high-resolution satellite imagery. ai.facebook.com/blog/mapping…
Austin Corotan retweeted
Congrats to our AI team for matching the top GLUE benchmark performance! We believe strongly in open & collaborative research and thank @GoogleAI for releasing BERT. It led to RoBERTa, our robustly optimized system that was trained longer, on more data. gluebenchmark.com/leaderboar…
Austin Corotan retweeted
Check out Evolved Transformer, a new state-of-the-art Transformer architecture for natural language processing, derived using a fresh approach to evolution-based neural architecture search. Learn all about it here → goo.gle/2IJ5QSK
Austin Corotan retweeted
Amazing!! Deep Learning-based NLP techniques are going to revolutionize the way we write software. Here's Deep TabNine, a GPT-2 model trained on around 2 million files from GitHub. Details at tabnine.com/blog/deep #nlproc
Austin Corotan retweeted
We recently open-sourced a state-of-the-art deep learning recommendation model (DLRM) implemented using @PyTorch and @caffe2ai: ai.facebook.com/blog/dlrm-an…
“AI’s Growing Role in Musical Composition” by Synced link.medium.com/qfH1niaXaY
Austin Corotan retweeted
In our new paper arxiv.org/abs/1907.02544 we show that GANs can be harnessed for unsupervised representation learning, with state-of-the-art results on ImageNet. Reconstructions, as shown below, tend to emphasise high-level semantics over pixel-level details.






