Shreyansh Singh

MAY 28, 2023

Paper : Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training Link : [link] Authors : Hong Liu, Zhiyuan Li, David Hall, Percy Liang, Tengyu Ma Code : [link] I have also released an annotated version of the paper. Adam and its variants have become the somewhat default optimizers which are used in LLM pretraining.

Deep Learning 52

Deep Learning Deep Learning 52

Explosion

NOVEMBER 16, 2021

Machine Learning Engineers who turn prototypes into production-ready software face difficulties with the lack of tooling and best-practices. I’ve been using spaCy for a few years now, as I did a lot of NLP projects both during my studies and previous work. With spaCy v3, you don’t have to write your own training loop anymore.

Machine Learning 52

Machine Learning Machine Learning Python Data Preparation 52

DrivenData Labs

APRIL 10, 2024

Developing new tools to use satellites for monitoring and understanding kelp forests is critical for us to understand where and how kelp forests are changing.” Results ¶ In this semantic segmentation challenge, the goal was to create an algorithm that predicts the presence or absence of kelp canopy using satellite imagery.

Deep Learning 130

Deep Learning Deep Learning Machine Learning Machine Learning 130

PyImageSearch

OCTOBER 2, 2023

Home Table of Contents A Deep Dive into Variational Autoencoder with PyTorch Introduction Comparison with Convolutional Autoencoder Architecture Latent Space Loss Function Why Does VAE Stand Out? Using the renowned Fashion-MNIST dataset, we’ll guide you through understanding its nuances. Let’s get started!

Deep Learning 120

Deep Learning Deep Learning Clustering Computer Science 120

PyImageSearch

NOVEMBER 6, 2023

Home Table of Contents Image Segmentation with U-Net in PyTorch: The Grand Finale of the Autoencoder Series Introduction U-Net Framework Configuring Your Development Environment Need Help Configuring Your Development Environment? Let’s embark on this grand finale together!

Deep Learning 67

Deep Learning Deep Learning Python Data Preparation 67

PyImageSearch

OCTOBER 23, 2023

Home Table of Contents Generating Faces Using Variational Autoencoders with PyTorch Configuring Your Development Environment Need Help Configuring Your Development Environment? Our journey begins with training a VAE on this dataset, setting the stage for a series of captivating experiments. Let’s dive in!

Deep Learning 67

Deep Learning Deep Learning Computer Science Computer Science 67

Mlearning.ai

APRIL 6, 2023

Problem statement Let’s say we need to classify a large number of tweets twice a day, so we will build an inference data pipeline at scale by triggering the SageMaker batch inference job and creating an end-to-end workflow using Apache Airflow on the Tweets dataset. Let’s look at some of the real-world batch inference use cases.

Data Pipeline 52

Data Pipeline ML ML AWS 52

PyImageSearch

JANUARY 22, 2024

To learn how to get started with using diffusers, just keep reading. Introduction In this tutorial, we will use the Diffusers library from Hugging Face. After training, we can use the Diffusion Model to generate data by simply passing randomly sampled noise through the learned denoising process.

Deep Learning 64

Deep Learning Deep Learning Algorithm Artificial Intelligence 64

AWS Machine Learning Blog

OCTOBER 23, 2023

This post is co-authored by Anatoly Khomenko, Machine Learning Engineer, and Abdenour Bezzouh, Chief Technology Officer at Talent.com. The system is developed by a team of dedicated applied machine learning (ML) scientists, ML engineers, and subject matter experts in collaboration between AWS and Talent.com.

AWS 90

AWS Deep Learning Deep Learning Machine Learning 90

PyImageSearch

JULY 17, 2023

Home Table of Contents Implementing a Convolutional Autoencoder with PyTorch Configuring Your Development Environment Need Help Configuring Your Development Environment? visualizing the latent space, uniform sampling of data points from this latent space, and recreating images using these sampled points).

Deep Learning 98

Deep Learning Deep Learning Python Machine Learning 98

AWS Machine Learning Blog

AUGUST 24, 2023

Today, we’re pleased to announce the preview of Amazon SageMaker Profiler , a capability of Amazon SageMaker that provides a detailed view into the AWS compute resources provisioned during training deep learning models on SageMaker. In this post, we walk you through the capabilities of SageMaker Profiler.

AWS 77

AWS Deep Learning Deep Learning ML 77

Mlearning.ai

MAY 4, 2023

This post briefly and with an example shows how to profile a training task of a model with the help of PyTorch profiler. Developers use profiling tools for understanding the behavior of their code to be able to optimize it. The following posts show how to use TensorFlow and TensorBoard. device), target.to(device)

Machine Learning 52

Machine Learning Machine Learning ML ML 52

Flipboard

SEPTEMBER 4, 2023

Home Table of Contents Getting Started with Docker for Machine Learning Overview: Why the Need? This lesson is the 1st of a 3-part series on Docker for Machine Learning : Getting Started with Docker for Machine Learning (this tutorial) Lesson 2 Lesson 3 Overview: Why the Need? What Are Containers? What Are Containers?

Machine Learning 109

Machine Learning Machine Learning Deep Learning Deep Learning 109

AWS Machine Learning Blog

DECEMBER 14, 2023

This post is co-authored by Anatoly Khomenko, Machine Learning Engineer, and Abdenour Bezzouh, Chief Technology Officer at Talent.com. In line with this mission, Talent.com collaborated with AWS to develop a cutting-edge job recommendation engine driven by deep learning, aimed at assisting users in advancing their careers.

ETL 83

ETL AWS ML ML 83

The MLOps Blog

APRIL 20, 2023

In such cases, consider padding images or using techniques like random cropping during data augmentation to maintain the original aspect ratio while still providing input of consistent dimensions to the network. These techniques combine multiple images or labels, encouraging the model to learn more robust features.

ML 64

ML ML Cross Validation Data Quality 64

AWS Machine Learning Blog

NOVEMBER 10, 2023

Creating high-performance machine learning (ML) solutions relies on exploring and optimizing training parameters, also known as hyperparameters. Hyperparameter optimization (HPO) can lead to faster training times, improved model accuracy, and better generalization to new data.

ML 89

ML ML Algorithm Python 89

AWS Machine Learning Blog

JULY 5, 2023

By predicting vehicle failures and scheduling maintenance and repairs, you’ll reduce downtime, improve safety, and boost productivity levels. What if we could apply deep learning techniques to common areas that drive vehicle failures, unplanned downtime, and repair costs? The solution outlined in the post is available on GitHub.

AWS 69

AWS Deep Learning Deep Learning ML 69

Flipboard

FEBRUARY 16, 2023

Modern model pre-training often calls for larger cluster deployment to reduce time and cost. At the server level, such training workloads demand faster compute and increased memory allocation. As models grow to hundreds of billions of parameters, they require a distributed training mechanism that spans multiple nodes (instances).

Clustering 106

Clustering AWS Deep Learning Deep Learning 106

AWS Machine Learning Blog

MAY 9, 2023

In addition, you can now use Application Auto Scaling with provisioned concurrency to address inference traffic dynamically based on target metrics or a schedule. In this post, we discuss what provisioned concurrency and Application Auto Scaling are, how to use them, and some best practices and guidance for your inference workloads.

AWS 66

AWS Machine Learning Machine Learning ML 66

Snorkel AI

FEBRUARY 21, 2024

Trained on internet-scale datasets, off-the-shelf LLMs handle many general reasoning tasks remarkably well without any additional training. LoRA shrinks the difficulty of training and fine-tuning large language models (LLMs) by reducing the number of trainable parameters and producing lightweight and efficient models.

Data Scientist 52

Data Scientist Machine Learning Machine Learning Algorithm 52

Snorkel AI

FEBRUARY 21, 2024

Trained on internet-scale datasets, off-the-shelf LLMs handle many general reasoning tasks remarkably well without any additional training. LoRA shrinks the difficulty of training and fine-tuning large language models (LLMs) by reducing the number of trainable parameters and producing lightweight and efficient models.

Data Scientist 52

Data Scientist Machine Learning Machine Learning Algorithm 52

Flipboard

MARCH 9, 2023

Hundreds of software as a service (SaaS) applications are being developed around these pre-trained models, which are either directly served to end-customers, or fine-tuned first on a per-customer basis to generate personal and unique content (such as avatars, stylized photo edits, video game assets, domain-specific text, and more).

AWS 106

AWS AI AI ML 106

AWS Machine Learning Blog

JANUARY 9, 2023

Machine learning (ML) applications are complex to deploy and often require the ability to hyper-scale, and have ultra-low latency requirements and stringent cost budgets. Use cases such as fraud detection, product recommendations, and traffic prediction are examples where milliseconds matter and are critical for business success.

ML 73

ML ML AWS Deep Learning 73