Monthly Edition

When I was just getting started in Data Science, I never thought I would need to tackle deep learning. Deep learning isn’t a concept for newbies! I naively thought that I could avoid it. Suddenly, just months into my journey, I was trying to optimize a task by building a recommendation system and needed to understand which NLP model would fit my problem and why. It was time to face the music.
As I began to dive into the topic, I realized that building a deep learning model is a lot like putting a jigsaw puzzle together without looking at the picture on the box. First, we pick out the pieces that we identify as the edges due to the shape. Next, we separate the rest of the puzzle pieces by color. Based on the colors of the edge pieces, we might be able to guess the approximate location of each color group. After that, we pick out the pieces within a subgroup of colors which we can easily identify are related and start to put them together. Piece by piece, we realize it’s Van Gogh’s The Night Café.
Like this analogy, a Deep Learning model is a masterpiece composed of many simpler concepts and functions. This idea is what makes deep learning such a powerful and widely used technique. Whether you are a newbie, a PhD in the tech field or anyone who cares about society, you will run into a deep learning topic sooner than you think. To help you learn more, we’ve put together some of our favorite picks on this topic, from introductory ideas to the state-of-art techniques. We hope they will shed new light on your current understanding and help you navigate this journey.
Linda Chen, Editor at Towards Data Science.
The Roadmap of Mathematics for Deep Learning
Understanding the inner workings of neural networks from the ground-up
by Tivadar Danka – 19 min read
Deep Learning with CIFAR-10
Image Classification using CNN
by Aarya Brahmane – 10 min read
Solve real-world problems using Deep Learning & Artificial Intelligence
Not your usual object detection blog
By Vaishnavi Dwivedi – 6 min read
Do you Really Need A GPU For Deep Learning?
Is acquiring a GPU an essential requirement for deep learning? Understanding GPU, its benefits, and exploring alternatives
By Bharath K – 7 min read
My 3-year journey: From zero Python to Deep Learning competition master
The path I followed since starting to learn Python back in 2017 up to became a Kaggle competition master with a solo gold medal in middle 2019. A story to inspire you to pursue your goals and never give up.
By Miguel Pinto – 6 min read
Deep learning on graphs: successes, challenges, and next steps
This is the first in a series of posts where I will discuss the evolution and future trends in the field of deep learning on graphs.
By Michael Bronstein – 7 min read
Deep learning isn’t hard anymore
At least, building software with deep learning isn’t
By Caleb Kaiser – 6 min read
MacBook Pro for Deep Learning? Let’s Try.
How will it compare against Nvidia GPU powered laptop?
By Dario Radečić – 4 min read
New podcasts
- Edouard Harris – Emerging problems in machine learning: making AI "good"
- Tim Rocktäschel— Deep reinforcement learning, symbolic learning and the road to AGI
- Rohin Shah – Effective altruism, AI safety, and learning human preferences from the state of the world
We also thank all the great new writers who joined us recently Federico Urena, Jason Yonglin Wu, Vaishnavi Dwivedi, Nicholas Lewis, Anjali Bhardwaj, Chris McCormick, Amir Afianian, Thouheed Gaffoor, Yingyuan (Valerie) Zhang, Diane Tunnicliffe, Nikhil Bhandari, Patrick Da Silva, Saurav Singla, Timo Bohnstedt, Alexandros Korkovelos, Vicky Yu, Das Wijesundera, Tyler Harris, Gabriel Luciano Pietrafesa, Irene P, Alireza Koochali, Mihail-Iulian Pleșa, Daniele Micci-Barreca, and many others. We invite you to take a look at their profiles and check out their work.