- ICLR 2019 highlights: Ian Goodfellow and GANs, Adversarial Examples, Reinforcement Learning, Fairness, Safety, Social Good, and all that jazz - May 27, 2019.
We provide an overview of the main themes and topics discussed at this years International Conference on Learning Representations (ICLR).
Adversarial, GANs, Ian Goodfellow, ICLR, New Orleans, Reinforcement Learning, Social Good
- Deep Compression: Optimization Techniques for Inference & Efficiency - Mar 20, 2019.
We explain deep compression for improved inference efficiency, mobile applications, and regularization as technology cozies up to the physical limits of Moore's law.
Compression, Convolutional Neural Networks, Deep Learning, ICLR, Inference, Optimization, Regularization
- Neural Networks seem to follow a puzzlingly simple strategy to classify images - Mar 5, 2019.
We explain why state-of-the-art Deep Neural Networks can still recognize scrambled images perfectly well and how this helps to uncover a puzzlingly simple strategy that DNNs seem to use to classify natural images.
Classification, Deep Learning, Deep Neural Network, ICLR, Image Classification, ImageNet, Neural Networks
- 10 Exciting Ideas of 2018 in NLP - Jan 16, 2019.
We outline a selection of exciting developments in NLP from the last year, and include useful recent papers and images to help further assist with your learning.
BERT, Bias, ICLR, Machine Translation, NLP, Transformer, Unsupervised Learning
- The Two Phases of Gradient Descent in Deep Learning - May 12, 2017.
In short, you reach different resting placing with different SGD algorithms. That is, different SGDs just give you differing convergence rates due to different strategies, but we do expect that they all end up at the same results!
Deep Learning, ICLR, Neural Networks
- The ICLR Experiment: Deep Learning Pioneers Take on Scientific Publishing - Feb 15, 2016.
Deep learning pioneers Yann LeCun and Yoshua Bengio have undertaken a grand experiment in academic publishing. Embracing a radical level of transparency and unprecedented public participation, they've created an opportunity not only to find and vet the best papers, but also to gather data about the publication process itself.
Academics, arXiv, Deep Learning, ICLR, Neural Networks, Yann LeCun, Yoshua Bengio, Zachary Lipton