The Framework Uber Uses for Designing Optimal Statistical Experiments
Author(s): Jesus Rodriguez Originally published on Towards AI. OED enables the scoring and optimization experiments using Pyro’s probabilistic programming model. Image Credit: Uber I recently started an AI-focused educational newsletter, that already has over 100,000 subscribers. TheSequence is a no-BS (meaning no …
Oriented FAST and Rotated BRIEF (ORB)
Author(s): Garima Nishad Originally published on Towards AI. So first let’s get a general idea about what it does & how it works. Then we’ll see both of these algorithms separately i.e. FAST and BRIEF. Fast and brief, are a feature detection …
An Intuitive Introduction to Document Vector(Doc2Vec)
Author(s): Manish Nayak Originally published on Towards AI. Intro to Doc2Vec U+007C Towards AI Introduction Doc2Vec is an extension of Word2vec that encodes entire documents as opposed to individual words. You can read about Word2Vec in my previous post. Doc2Vec vectors represent …
Near-Optimal Representation Learning for Hierarchical Reinforcement Learning
Author(s): Sherwin Chen Originally published on Towards AI. Beyond Hierarchical Reinforcement learning with Off-policy correction(HIRO) This is the second post of the series, in which we will talk about a novel Hierarchical Reinforcement Learning built upon HIerarchical Reinforcement learning with Off-policy correction(HIRO) …
HAC: Learning Multi-Level Hierarchies with Hindsight
Author(s): Sherwin Chen Originally published on Towards AI. Hindsight experience replay for multi-level hierarchies the 4-level HAC agent on the inverted pendulum We discuss a novel Hierarchical Reinforcement Learning(HRL) framework that can efficiently learn multiple levels of policies in parallel. Experiments shows, …
Demystifying the Architecture of Long Short Term Memory (LSTM) Networks
Author(s): Manish Nayak Originally published on Towards AI. Architecture of LSTMs U+007C Towards AI Introduction In my previous article, I explain RNNs’ Architecture. RNNs are not perfect and they mainly suffer from two major issues exploding gradients and vanishing gradients. Exploding gradients …
How to Use scikit-learn ‘eli5’ Library to Compute Permutation Importance?
Author(s): Abhinav Prakash Originally published on Towards AI. Feature Permutation Importance with ‘eli5’ U+007C Towards AI Understanding the workings of scikit-learn’s ‘eli5’ library to compute feature importance on a sample housing dataset and interpreting its results cc: Forbes Most of the Data …
The ABCs of PyTorch in 4 Minutes
Author(s): Rohit Sharma Originally published on Towards AI. PyTorch 101 U+007C Towards AI Introducing the basics of PyTorch in four minutes, with sample code © AITS (www.ai-techsystems.com) This article helps newbies to get started with python PyTorch in 2 minutes with code …
MINE: Mutual Information Neural Estimation
Author(s): Sherwin Chen Originally published on Towards AI. Estimating mutual information using arbitrary neural networks through MINE Source: istock.com/ipopba Mutual information, also known as information gain, has been successfully used in the context of deep learning(which we will see soon) and deep …
DIM: Learning Deep Representations by Mutual Information Estimation and Maximization
Author(s): Sherwin Chen Originally published on Towards AI. Encoder Network Source: Pixabay This is our second article of the series about mutual information. In the previous articles, we have seen how to maximizes the mutual information between two variables via the MINE …
Image Classification using Deep Learning & PyTorch: A Case Study with Flower Image Data
Author(s): Avishek Nag Originally published on Towards AI. Classifying Flower images using Convolutional Deep Neural Network with PyTorch library Photo by Krystina rogers on Unsplash Classifying image data is one of the very popular usages of Deep Learning techniques. In this article, …
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 …
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 …
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 …
PEARL: Probabilistic Embeddings for Actor-Critic RL
Author(s): Sherwin Chen Originally published on Towards AI. A sample-efficient meta reinforcement learning method Top highlight Source: Unsplash Meta reinforcement learning could be particularly challenging because the agent has to not only adapt to the new incoming data but also find an …
Popular posts
Updates
Recent Posts
