DIAYN: Diversity Is All You Need
Author(s): Sherwin Chen Originally published on Towards AI. Top highlight Diving Into DIAYN U+007C Towards AI An Unsupervised Information-Based Method to Learn Diverse Skills Different skills learned by DIAYN without any extrinsic reward signal. Source: https://sites.google.com/view/diayn Introduction We discuss an information-based reinforcement …
Several Ways for Machine Learning Model Serving (Model as a Service)
Author(s): Edward Ma Originally published on Towards AI. Using Model as a Service (MaaS) on Cloud Platforms Top highlight Photo by Edward Ma on Unsplash No matter how well you build a model, no one knows it if you cannot ship model. …
@Bayes’ Theorem For Bae
Author(s): Michael Knight Originally published on Towards AI. Intro to Probability and Stats U+007C Towards AI Introduce someone to probability theory and statistics without scaring them off Source Bayes’ Theorem is something that confuses and frustrates many, but is not as awful …
How to Train MAML(Model-Agnostic Meta-Learning)
Author(s): Sherwin Chen Originally published on Towards AI. An elaborate explanation for MAML and more Top highlight Source: Pixabay Model-Agnostic Meta-Learning(MAML) has been growing more and more popular in the field of meta-learning since it’s first introduced by Finn et al. in …
Why Precision and Recall metric?
Author(s): Jalal Mansoori Originally published on Towards AI. What is a Class-imbalanced dataset? Image by Author Before answering the above question let me tell you my experience when I was learning about the evaluation of learning algorithms in classification problems. Currently, I …
Data Science 101 — A Short Course on Medium Platform with R and Python Code Included
Author(s): Benjamin Obi Tayo Ph.D. Originally published on Towards AI. Data Science 101 is intended for individuals that have some prior exposure or knowledge in data science concepts and are interested in practical applications beyond what is offered in most introductory-level data …
EMI: Exploration with Mutual Information
Author(s): Sherwin Chen Originally published on Towards AI. A novel exploration method based on representation learning Source: Photo by Andrew Neel on Unsplash Reinforcement learning could be hard when the reward signal is sparse. In these scenarios, exploration strategy becomes essentially important: …
New Model for Word Embeddings which are Resilient to Misspellings (MOE)
Author(s): Edward Ma Originally published on Towards AI. Photo by Edward Ma on Unsplash Traditional word embeddings are good at solving lots of natural language processing (NLP) downstream problems such as documentation classification and named-entity recognition (NER). However, one of the drawbacks …
APTOS 2019 Blindness Detection — Playing around with ResNeXts and Progressive NASNet
Author(s): Luka Chkhetiani Originally published on Towards AI. APTOS 2019 Blindness Detection U+007C Towards AI A while ago Kaggle announced challenge: APTOS 2019 Blindness Detection — Detect diabetic retinopathy to stop blindness before it’s too late. The idea of competition is to …
Artificial Intelligence Without the Utopian Promise-land and Dystopian Armageddon
Author(s): Davor Petreski Originally published on Towards AI. The Future of AI U+007C Towards AI Before you start reading, think of 3 possible scenarios for the future of Artificial Intelligence (AI). If I asked you to think of 3 possible scenarios for …
Recent Posts
