Rani HorevinTowards Data ScienceThe Evolved Transformer — Enhancing Transformer with Neural Architecture SearchNeural architecture search (NAS) is the process of algorithmically searching for new designs of neural networks. Though researchers have…7 min read·Mar 14, 2019--2--2
Rani HorevinTowards Data ScienceXLM — Enhancing BERT for Cross-lingual Language ModelCross-lingual Language Model Pretraining5 min read·Feb 12, 2019--5--5
Rani HorevinTowards Data ScienceIdentifying and Correcting Label Bias in Machine LearningIn a new paper from Google, researchers propose a novel technique to train machine learning algorithms fairly even with a biased dataset.6 min read·Feb 9, 2019--2--2
Rani HorevinTowards Data ScienceTransformer-XL Explained: Combining Transformers and RNNs into a State-of-the-art Language ModelLanguage modeling has become an important NLP technique thanks to the ability to apply it to various NLP tasks, such as machine…7 min read·Jan 17, 2019--2--2
Rani HorevinTowards Data ScienceExplained: Multilingual Sentence Embeddings for Zero-Shot TransferApplying a Single Model on 93 Languages7 min read·Jan 7, 2019--2--2
Rani HorevinSnipSnip — December Update & 2018 SummaryGreetings to the Snip community!2 min read·Jan 3, 2019----
Rani HorevinTowards Data ScienceExplained: A Style-Based Generator Architecture for GANs - Generating and Tuning Realistic…NVIDIA’s novel architecture for Generative Adversarial Networks9 min read·Dec 30, 2018--9--9
Rani HorevinTowards Data ScienceSlowFast Explained - Dual-mode CNN for Video UnderstandingState-of-the-art Deep Learning architecture inspired by the visual mechanism of primates6 min read·Dec 27, 2018--5--5
Rani HorevinTowards Data ScienceKuzushiji-MNIST - Japanese Literature Alternative Dataset for Deep Learning TasksPlus our VGG-ResNet ensemble model with state-of-the-art results3 min read·Dec 14, 2018----
