Up to Speed on Deep Learning: May Update

Sharing some of the latest research, announcements, and resources on deep learning.

By Isaac Madan (email)

Continuing our series of deep learning updates, we pulled together some of the awesome resources that have emerged since our last post. In case you missed it, here are our past updates: April part 2, April part 1, March part 1, February, November, September part 2 & October part 1, September part 1, August part 2, August part 1, July part 2, July part 1, June, and the original set of 20+ resources we outlined in April 2016. As always, this list is not comprehensive, so let us know if there’s something we should add, or if you’re interested in discussing this area further.

Announcements & Research

Caffe2 release by Facebook. Open-sourcing the first production-ready release of Caffe2 — a lightweight and modular deep learning framework emphasizing portability while maintaining scalability and performance. Shipping with tutorials and examples that demonstrate learning at massive scale. Deployed at Facebook.

Speech synthesis with minimal training data by Lyrebird. PhD students from the University of Montreal announce, they are developing new speech synthesis technologies which, among other features, allow us to copy the voice of someone with very little data.

Understanding deep learning requires rethinking generalization by Google researchers. An ICLR 2017 Best Paper, through extensive systematic experiments, we show how the traditional approaches fail to explain why large neural networks generalize well in practice, and why understanding deep learning requires rethinking generalization.

The Synthetic data vault by MIT researchers. Describes machine learning system that automatically creates synthetic data — with the goal of enabling data science efforts that, due to a lack of access to real data, may have otherwise not left the ground. This synthetic data is completely different from that produced by real users.

Resources

The Modern History of Object Recognition — Infographic by Đặng Hà Thế Hiển. Summarizes important concepts in object recognition, like bounding box regression and transposed convolution, and also outlines the history of deep learning approaches to object recognition since 2012.

The Deep Learning Roadmap by Carlos Perez. A map that categorizes the various research threads and advancements within deep learning. A useful categorization as you follow developments in the space.

Failures of Deep Learning (video) by Shai Shalev-Shwartz. Lecture on three families of problems for which existing deep learning algorithms fail. We illustrate practical cases in which these failures apply and provide a theoretical insight explaining the source of difficulty. Slides here.

Introduction to Deep Learning by MIT. A week-long intro to deep learning methods with applications to machine translation, image recognition, game playing, image generation and more. A collaborative course incorporating labs in TensorFlow and peer brainstorming along with lectures. All lecture slides and videos available.

A Brief History of CNNs in Image Segmentation: From R-CNN to Mask R-CNN by Dhruv Parthasarathy. An overview of CNN developments applied to image segmentation.

Deep learning for satellite imagery via image segmentation by Arkadiusz Nowaczynski. A top performing team of a recent Kaggle competition discusses their deep learning approach to image segmentation of satellite imagery and shares lessons learned.

Keras Cheatsheet by DataCamp. Cheatsheet for the six steps that you can go through to make neural networks in Python with the Keras library.

Tutorials

How to Build a Recurrent Neural Network in TensorFlow by Erik Hallström. This is a no-nonsense overview of implementing a recurrent neural network (RNN) in TensorFlow. Both theory and practice are covered concisely, and the end result is running TensorFlow RNN code.

Interpretability via attentional and memory-based interfaces, using TensorFlow by Goku Mohandas. A gentle introduction to attentional and memory-based interfaces in deep neural architectures, using TensorFlow. Incorporating attention mechanisms is very simple and can offer transparency and interpretability to our complex models. GitHub repo here.

Recurrent Neural Networks & LSTMs by Rohan Kapur. A gentle and detailed introduction to RNNs. See the rest of their blog for more fantastic introductory resources.

Deep Neural Network from scratch by Florian Courtial. Tutorial on how deep neural networks work and a Python implementation with TensorFlow.

The GAN Zoo by Avinash Hindupur. List of all named GANs and their respective papers.


By Isaac Madan. Isaac is an investor at Venrock (email). If you’re interested in deep learning, we’d love to hear from you.

Requests for Startups is a newsletter of entrepreneurial ideas & perspectives by investors, operators, and influencers.

7 Insightful Quotes from Amazon’s Letter to Shareholders

Every year, Jeff Bezos publishes a letter to Amazon shareholders. These letters tend to be an interesting lens into the company and its progress, as well as a source of insightful snippets about building & leading an iconic business. We thought we’d share a few of our favorite nuggets from Bezos’ 2017 letter published earlier this month. We did the same for last year’s letter as well here.

Continue reading “7 Insightful Quotes from Amazon’s Letter to Shareholders”

Up to Speed on Deep Learning: April Update, Part 2

Sharing some of the latest research, announcements, and resources on deep learning.

By Isaac Madan (email)

Continuing our series of deep learning updates, we pulled together some of the awesome resources that have emerged since our last post. In case you missed it, here are our past updates: April part 1, March, February, November, September part 2 & October part 1, September part 1, August part 2,August part 1, July part 2, July part 1, June, and the original set of 20+ resources we outlined in April 2016. As always, this list is not comprehensive, so let us know if there’s something we should add, or if you’re interested in discussing this area further.

Continue reading “Up to Speed on Deep Learning: April Update, Part 2”

Up to Speed on Deep Learning: March Update, Part 2

Sharing some of the latest research, announcements, and resources on deep learning.

By Isaac Madan (email)

Continuing our series of deep learning updates, we pulled together some of the awesome resources that have emerged since our last post. In case you missed it, here are our past updates: March part 1, February, November, September part 2 & October part 1, September part 1, August part 2, August part 1, July part 2, July part 1, June, and the original set of 20+ resources we outlined in April 2016. As always, this list is not comprehensive, so let us know if there’s something we should add, or if you’re interested in discussing this area further.

Continue reading “Up to Speed on Deep Learning: March Update, Part 2”

Up to Speed on Deep Learning: March Update

Sharing some of the latest research, announcements, and resources on deep learning.

By Isaac Madan

Continuing our series of deep learning updates, we pulled together some of the awesome resources that have emerged since our last post. In case you missed it, here are our past updates: March part 1, November, September part 2 & October part 1, September part 1, August part 2, August part 1, July part 2, July part 1, June, and the original set of 20+ resources we outlined in April. As always, this list is not comprehensive, so let us know if there’s something we should add, or if you’re interested in discussing this area further.

Continue reading “Up to Speed on Deep Learning: March Update”

Channel Sales: The 3 Key Attributes You Need to Know to Scale Your Business

Here’s what to consider when approaching partners & resellers to help you sell more product.

By Jaimin Patel, Ascanio Guarini, and Isaac Madan

There are many factors that play a key role in picking the right indirect routes to market (aka partner strategy, channel selling) for a company looking to scale their revenue beyond direct sales.

Continue reading “Channel Sales: The 3 Key Attributes You Need to Know to Scale Your Business”

Up to Speed on Deep Learning: February Update

Sharing some of the latest research, announcements, and resources on deep learning.

By Isaac Madan

Continuing our series of deep learning updates, we pulled together some of the awesome resources that have emerged since our last post. In case you missed it, here are our past updates: November, September part 2 & October part 1, September part 1, August part 2, August part 1, July part 2, July part 1, June, and the original set of 20+ resources we outlined in April. As always, this list is not comprehensive, so let us know if there’s something we should add, or if you’re interested in discussing this area further.

Continue reading “Up to Speed on Deep Learning: February Update”

Effective Recruiting Metrics for Fast-Growing Startups


We spent the better part of 2015 working with fast-growing tech companies on their internal HR & recruiting analytics. Effective recruiting can be incredibly challenging: First Round Capital’s State of Startups 2016 Report assessed that talent acquisition is founders’ biggest concern for the second year in a row. Recruiting metrics help to identify problems and optimize the talent acquisition process: if you can’t measure it, you can’t improve it. Below we share some of the most common metrics we observed across startups that serve as the basis for understanding and improving your recruiting process. The list below isn’t comprehensive, nor applicable for everyone, but it’s a good place to start.

Continue reading “Effective Recruiting Metrics for Fast-Growing Startups”

Startup DB: Search for relevant, curated posts by entrepreneurs & investors

The Mattermark Daily is an excellent daily newsletter that curates first-hand perspectives on entrepreneurship, investing, sales, hiring, and more, as it emerges everyday. As a weekend hack, we deep-indexed every article featured in the Daily over the past few years, and built StartupDB: a simple search interface so you can find the best, most relevant startup content from the Daily when you need it. We’ve been using it internally to field questions from readers and pull together some of the best startup resources — for example, this post here on 10 excellent resources for enterprise sales.

Give StartupDB a try here.


We’d love to hear your feedback & thoughts via email. Special thanks to Nick Frost, Editor of the Mattermark Daily, for his support.

Subscribe to our email newsletter here. Requests for Startups is a newsletter of entrepreneurial ideas & perspectives by investors, operators, and influencers.