Open in app

Sign In

Write

Sign In

James Loy
James Loy

7K Followers

Home

About

Published in

Towards Data Science

·Pinned

How to build your own Neural Network from scratch in Python

A beginner’s guide to understanding the inner workings of Deep Learning — Update: When I wrote this article a year ago, I did not expect it to be this popular. Since then, this article has been viewed more than 450,000 times, with more than 30,000 claps. It has also made it to the front page of Google, and it is among the…

Machine Learning

7 min read

How to build your own Neural Network from scratch in Python
How to build your own Neural Network from scratch in Python
Machine Learning

7 min read


Published in

Towards Data Science

·Sep 6, 2022

Global Context Vision Transformers (GC ViT)— Nvidia’s new SOTA Image Model

In-depth Explanation and Visualizations — Introduction Nvidia has recently published a new vision transformer, titled the Global Context Vision Transformer (GC ViT) (Hatamizadeh et al., 2022). GC ViT introduced a novel architecture that leverages both global attention and local attention, allowing it to model both short-range and long-range spatial interactions. The clever techniques used by the…

Deep Learning

6 min read

Global Context Vision Transformers — Nvidia’s new SOTA Image Model
Global Context Vision Transformers — Nvidia’s new SOTA Image Model
Deep Learning

6 min read


Published in

Towards Data Science

·May 20, 2022

A Comprehensive Guide to Microsoft’s Swin Transformer

In-depth Explanation and Animations — Introduction Swin Transformer (Liu et al., 2021) is a transformer-based deep learning model with state-of-the-art performance in vision tasks. Unlike the Vision Transformer (ViT) (Dosovitskiy et al., 2020) which precedes it, Swin Transformer is highly efficient and has greater accuracy. Due to these desirable properties, Swin Transformers are used as the…

Deep Learning

7 min read

A Comprehensive Guide to Microsoft’s Swin Transformer
A Comprehensive Guide to Microsoft’s Swin Transformer
Deep Learning

7 min read


Published in

Towards Data Science

·Mar 1, 2021

NFNets Explained — DeepMind’s New State-Of-The-Art Image Classifier

Is this the beginning of the end for Batch Normalization? — Introduction DeepMind has recently released a new family of image classifiers that achieved a new state-of-the-art accuracy on the ImageNet dataset. This new family of image classifiers, named NFNets (short for Normalizer-Free Networks), achieves comparable accuracy to EfficientNet-B7, while having a whopping 8.7x faster train time.

Deep Learning

7 min read

NFNets Explained — DeepMind’s New State-Of-The-Art Image Classifier
NFNets Explained — DeepMind’s New State-Of-The-Art Image Classifier
Deep Learning

7 min read


Published in

Towards Data Science

·Nov 2, 2020

Fundamentals of Generative Adversarial Networks

GANs — Illustrated, explained and coded — Introduction In 2014, a then-unknown Ph.D. student named Ian Goodfellow introduced Generative Adversarial Networks (GANs) to the world. GANs were unlike anything the AI community had seen, and Yann LeCun described it as “the most interesting idea in the last 10 years in ML”. Since then, much research effort have poured…

Generative Adversarial

9 min read

Fundamentals of Generative Adversarial Networks
Fundamentals of Generative Adversarial Networks
Generative Adversarial

9 min read


Published in

Towards Data Science

·Oct 19, 2020

Deep Learning based Recommender Systems

A gentle introduction to modern movie recommenders — Traditionally, recommender systems are based on methods such as clustering, nearest neighbor and matrix factorization. However, in recent years, deep learning has yielded tremendous success across multiple domains, from image recognition to natural language processing. Recommender systems have also benefited from deep learning’s success. In fact, today’s state-of-the-art recommender systems…

Deep Learning

10 min read

Deep Learning based Recommender Systems
Deep Learning based Recommender Systems
Deep Learning

10 min read


Mar 11, 2019

Following up from Medium’s most popular Neural Network article of 2018

A year ago, I posted my very first article on Medium titled ‘How to build your own Neural Network from scratch in Python’. How to build your own Neural Network from scratch in Python A beginner’s guide to understanding the inner workings of Deep Learningtowardsdatascience.com Inspired by the many articles I read here, I wanted to contribute to the community by writing a beginner’s guide to Neural Networks in Python. …

Machine Learning

3 min read

Following up from Medium’s most popular neural network article of 2018
Following up from Medium’s most popular neural network article of 2018
Machine Learning

3 min read

James Loy

James Loy

7K Followers

Data Scientist • Author & Writer

Following
  • Sean Kernan

    Sean Kernan

  • Sik-Ho Tsang

    Sik-Ho Tsang

  • Synced

    Synced

  • Parul Pandey

    Parul Pandey

  • Jesus Rodriguez

    Jesus Rodriguez

See all (31)

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech

Teams