Sharpened Cosine Similarity: Part 2

A lot has happened since my last post on the Sharpened Cosine Similarity layer. In this…

A guide to TensorLayer for efficient deep learning development

TensorLayer is a modular Python toolkit that provides simple modules to help academics and engineers build…

Google unveils differential privacy tool for Python developers processing data | ZDNet

Google said it has been working with OpenMined for a year on the effort. Read more…

Everyday objects can run artificial intelligence programs

Nontraditional hardware could help neural networks operate faster and more efficiently than computer chips. Read more…

Meta’s ‘data2vec’ is a step toward One Neural Network to Rule Them All | ZDNet

By eschewing data-specific outputs for internal representations, Meta aims for a more-general sort of AI. Read…

TinyML is bringing neural networks to small microcontrollers

IBM and MIT have created a new deep learning technique that can run CNNs on low-power,…

Uber Releases V1.1 of Orbit: A Python Package to Perform Bayesian Time-Series Analysis and Forecasting

Uber Releases V1.1 of Orbit: A Python Package to Perform Bayesian Time-Series Analysis and Forecasting Read…

AI makes it possible to simulate 25 billion water molecules at once

Computer simulations of clouds of atoms and molecules must always trade scale for accuracy, but a…

What Is TinyML? – Technical Articles

Learn about a subsection of machine learning (ML) called Tiny Machine Learning (TinyML), what it is,…

The largest suite of cosmic simulations for AI training, free to download, already spurring discoveries

Totaling 4,233 universe simulations, millions of galaxies and 350 terabytes of data, a new release from…

OpenAI Releases GLIDE: A Scaled-Down Text-to-Image Model That Rivals DALL-E Performance | Synced

Text-to-image generation has been one of the most active and exciting AI fields of 2021. In…

TensorFlow 2.7.0 Released: All Major Updates & Features

Google launched the upgraded version of TensorFlow today. Read more at Analytics India Magazine…

The Deep-Learning Algorithm Can Guess an ATM PIN, Even With Keypads Covered

The algorithm only fails to guess the ATM PIN with 100% hand coverage. Whereas the attackers…

Google’s Gated Multi-Layer Perceptron Outperforms Transformers Using Fewer Parameters

Researchers at Google Brain have announced Gated Multi-Layer Perceptron (gMLP), a deep-learning model that contains only…

Are Patches All You Need? New Study Proposes Patches Are Behind Vision Transformers’ Strong Performance | Synced

Vision transformer architectures (ViTs) have achieved compelling performance across many computer vision tasks, often outperforming classical…

Stuck in GPT-3’s waitlist? Try out the AI21 Jurassic-1

The latest contender in the NLP arms race is AI21, with its 178 billion parameter model,…

A developer built an AI chatbot using GPT-3 that helped a man speak again to his late fiancée. OpenAI shut it down

Crackdown on open-ended, unfiltered simulations branded ‘a hyper-moral stance’ Read more…

OpenAI Sold its Soul for $1 Billion

The company behind GPT-3 and Codex isn’t as open as it claims. Read more at Medium…

My first gold in Kaggle: Tips and tricks for an NLP competition

Or how do solve a regression task with HuggingFace models. Read more at Medium…

How to Train a BERT Model From Scratch – KDnuggets

Meet BERT’s Italian cousin, FiliBERTo. Easy peasy 🙂 Read more at KDnuggets…