5041
New
The latest blog posts to take off on Hacker News. 6,335 posts.
5042
5043
AIs Named by AIs
Neural networks can be good at naming things, I’ve discovered. Recently I’ve been experimenting with a neural network called GPT-2, which OpenAI trained on a huge chunk of the internet. Thanks to a colab notebook implementation by Max Woolf, I’m able to fine-tune it on specific lists of data -
5044
5045
Machine learning systems are stuck in a rut
Machine learning systems are stuck in a rut Barham & Isard, HotOS’19 In this paper we argue that systems for numerical computing are stuck in a local basin of performance and programmabil…
5046
5047
AI Models Predict Breast Cancer with Radiologist-Level Accuracy
The IBM Research blog is the home for stories told by the researchers, scientists, and engineers inventing What’s Next in science and technology.
5048
5049
Logistic Regression from Bayes’ Theorem
In this post we’ll explore how we can derive logistic regression from Bayes’ Theorem. Starting with Bayes’ Theorem we’ll work our way to computing the log odds of our problem and the arrive at the inverse logit function. After reading this post you’ll have a much stronger intuition for how logistic
5050
Towards Reproducible Research with PyTorch Hub
Reproducibility is an essential requirement for many fields of research including those based on machine learning techniques. However, many machine learning publications are either not reproducible or are difficult to...
5051
Google Research Football: A Novel Reinforcement Learning Environment
Posted by Karol Kurach, Research Lead and Olivier Bachem, Research Scientist, Google Research, Zürich The goal of reinforcement learning (RL) is ...
5052
Chip design drastically reduces energy needed to compute with light
MIT researchers have developed a “photonic” artificial intelligence (AI) accelerator that computes using light instead of electricity — and consumes relatively little power in the process — to run massive neural networks millions of times more efficiently than today’s classical computers.
5053
5054
Language, trees, and geometry in neural networks
Language is made of discrete structures, yet neural networks operate on continuous data: vectors in high-dimensional space. A successful language-processing network must translate this symbolic information into some kind of geometric representation—but in what form? Word embeddings provide two well-known examples…
5055
Algorithm allows video editors to modify talking-head videos as if editing text
A new algorithm allows video editors to modify talking head videos as if they were editing text – copying, pasting, or adding and deleting words.
5056
5057
Using machine learning to estimate lost demand in a fulfillment chain
How Instacart uses Machine Learning to spot lost demand in its fulfillment chain
5058
Amazon Unveils New Alexa Dialog Modeling for Natural, Cross-Skill Conversations
Get the latest news and features about smart home, Alexa Built-in, and Alexa Gadgets.
5059
5060
Random Forest vs. Neural Network
Choosing between Random Forest and Neural Network depends on the data type. Random Forest suits tabular data, while Neural Network excels with images, audio, and text data.
5061
Cracking open the black box of automated machine learning
ATMSeer is an interactive visualization tool for users to see and control algorithms and hyperparameters of machine-learning (AutoML) systems. The work was developed by researchers in the MIT Laboratory for Information and Decision Systems (LIDS), Hong Kong University of Science and Technology (HKUST), and Zhejiang…
5062
Implementing a Convolutional Neural Network Using Only NumPy
A simple walkthrough of deriving backpropagation for CNNs and implementing it from scratch in Python.
5063
5064
5065
Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
Posted by Tali Dekel, Research Scientist and Forrester Cole, Software Engineer, Machine Perception The human visual system has a remarkable abili...
5066
5067
Implementing a Convolutional Neural Network from Scratch in Python
A simple guide to what CNNs are, how they work, and how to build one from scratch in Python.
5068
5069
Notes on Weight Initialization for Deep Neural Networks
Neural networks involve long sequence of multiplications, usually between a matrix and a vector, say \(a*x\). The result of this sequence of multiplications will either have a huge magnitude or be reduced to 0. We can divide \(a\) by a number ( scaling_factor ) to scale down its magnitude to the right level. Proper…
5070
Matrices as Tensor Network Diagrams
In the previous post, I described a simple way to think about matrices, namely as bipartite graphs. Today I'd like to share a different way to picture matrices—one which is used not only in mathematics, but also in physics and machine learning. Here's the basic idea. An $m\times n$ matrix $M$ with real entries…