Published in Towards Data Science·PinnedMember-onlyN-BEATS: Time-Series Forecasting with Neural Basis ExpansionA Deep Learning model for zero-shot time-series forecasting — There’s one thing that makes Time-Series Forecasting special. It was the only area of Data Science where Deep Learning and Transformers didn’t decisively outperform the other models. Let’s use the prestigious Makridakis M-competitions as a benchmark — a series of large-scale challenges that showcase the latest advances in the time-series…Time Series Forecasting12 min readTime Series Forecasting12 min read
Published in Towards Data Science·PinnedMember-onlyTemporal Fusion Transformer: Time Series Forecasting with Deep Learning — Complete TutorialCreate accurate and interpretable predictions — According to [2], Temporal Fusion Transformer outperforms all prominent Deep Learning models for time series forecasting. Including a featured Gradient Boosting Tree model for tabular time series data. But what is Temporal Fusion Transformer (TFT)[3] and why is it so interesting? In this article, we briefly explain the novelties of…Time Series Forecasting12 min readTime Series Forecasting12 min read
Published in Towards Data Science·PinnedMember-onlyThe Best Deep Learning Models for Time Series ForecastingEverything you need to know about Time Series and Deep Learning — Be sure to SUBSCRIBE here to never miss another article on data science topics, projects, guides and more! Preliminaries The landscape of Time Series forecasting has changed dramatically in the span of two years. The forth and fifth in the series of Makridakis M-competitions (better known as M4 and M5 competitions…Data Science10 min readData Science10 min read
Published in Towards Data Science·PinnedMember-onlyTemporal Fusion Transformer: Time Series Forecasting with InterpretabilityGoogle’s state-of-the-art Transformer has it all — Preliminaries First and foremost, let’s be clear: The era of tailoring a model to a single time series, either univariate or multivariate, is long gone. Nowadays, in the big data era, the creation of new data points is extremely cheap. Imagine a large electrical company having thousands of sensors that measure…Data Science13 min readData Science13 min read
Published in Towards Data Science·Nov 14Member-onlyDeepAR: Mastering Time-Series Forecasting with Deep LearningAmazon’s autoregressive deep network — A few years ago, time-series models worked on a single sequence only. Hence, if we had multiple time-series, one option was to create one model per sequence. Or, if we could “tabularize” our data, we could apply the gradient-boosted tree models — which work very well even today. The first…Time Series Forecasting9 min readTime Series Forecasting9 min read
Published in Geek Culture·Oct 17Member-onlyUse AI to Create Subtitles For Youtube Videos and Movies in 97 Languages — For FreeNo programming knowledge required. AI breakthroughs like CLIP [1] and Whisper [2] have made headlines not only because they are immensely useful — they are also open-source. Which means they are free for anyone to use. In a previous article, I wrote about Whisper, a Speech Recognition AI model capable…Artificial Intelligence5 min readArtificial Intelligence5 min read
Published in Towards Data Science·Oct 7Member-onlyWhisper: Transcribe & Translate Audio Files With Human-Level PerformanceAn AI model compatible with 97 languages — and how to use it — It is now clear that the general direction of Deep Learning research has fundamentally changed. A few years ago, the modus operandi of most innovative papers was this: Select a dataset X, build and train a novel model on that dataset, and prove your model was the best by reporting…Artificial Intelligence10 min readArtificial Intelligence10 min read
Published in Towards Data Science·Sep 26Member-onlyCLIP: The Most Influential AI Model From OpenAI — And How To Use ItFind out how the model works — coding example included — What do the recent AI breakthroughs, DALLE[1] and Stable Diffusion[2] have in common? They both use components of CLIP’s[3] architecture. Hence, if you want to grasp how those models work, understanding CLIP is a prerequisite. Besides, CLIP has been used to index photos on Unsplash. But what does CLIP do…Artificial Intelligence12 min readArtificial Intelligence12 min read
Published in Towards Data Science·Aug 31Member-onlyBuild a Named Entity Recognition App with StreamlitFrom building the app to deployment — with code included — In my previous article, we fine-tuned a Named Entity Recognition (NER) model, trained on the wnut_17[1] dataset. In this article, we show step-by-step how to integrate this model with Streamlit and deploy it using HugginFace Spaces. …Artificial Intelligence6 min readArtificial Intelligence6 min read
Published in Towards Data Science·Aug 12Member-onlyNamed Entity Recognition with Deep Learning (BERT) — The Essential GuideFrom data preparation to model training for NER tasks — and how to tag your own sentences — Update: You can now learn how to deploy this model with Streamlit! Nowadays, NLP has become synonymous with Deep Learning. But, Deep Learning is not the ‘magic bullet’ for every NLP task. For example, in sentence classification tasks, a simple linear classifier could work reasonably well. …Data Science6 min readData Science6 min read
