|
|
February 12 · Issue #78 · View online
The Wild Week in AI is a weekly AI & Deep Learning newsletter curated by @dennybritz.
|
|
If you enjoy the newsletter, please consider sharing it on Twitter, Facebook, etc! Really appreciate the support :)
|
|
|
Marketmuse Inc.’s M4 Lab (MarketMuse Montreal Machine Monograph Lab) is seeking an NLG Research Scientist to help create the next generation of content generation technologies. Your work will require deep understanding and experience with neural language models and generative deep learning techniques such as VAEs, VAE-GANs, GANs, cGANs, RL-GANs, attention mechanisms, conditional language models, LSTMs or other RNNs. We are a small team looking for top scientists excited to advance natural language generation and to have the opportunity to shape our newly formed lab’s research direction and vision. You can apply for our position here or write us at science@marketmuse.com.
|
|
The Limits of Artificial Intelligence and Deep Learning
Deep learning’s advances are the product of pattern recognition: neural networks memorize classes of things and more-or-less reliably know when they encounter them again. But most of the interesting problems in cognition aren’t classification problems at all.
|
Lightmatter aims to reinvent AI-specific chips with photonic computing and $11M in funding
Lightmatter is a startup that makes photonic chips that essentially perform calculations at the speed of light. It competes directly with GPU manufacturers and custom-built Deep Learning chips.
|
Paige.ai nabs $25M to bring machine learning to cancer pathology
Paige.ai, an acronym for Pathology AI Guidance Engine, has closed $25 million in Series A funding to build a system to help understand cancer pathology. It has exclusive access to its 25 million pathology slides as well as its intellectual property related to computational pathology.
|
Facial Recognition Is Accurate, if You’re a White Guy
A newly published paper studied the performance of three leading face recognition systems — by Microsoft, IBM and Megvii of China — by classifying how well they could guess the gender of people with different skin tones. Microsoft’s error rate for darker-skinned women was 21 percent, while IBM’s and Megvii’s rates were nearly 35 percent. They all had error rates below 1 percent for light-skinned males.
|
|
A Short Introduction to Entropy, Cross-Entropy and KL-Divergence
Entropy, Cross-Entropy, and KL-Divergence are often used in Machine Learning, in particular for training classifiers. In this short video, you will understand where they come from and why we use them in ML.
|
IMPALA: Scalable Distributed Deep RL in DMLab-30
Deep Reinforcement Learning has achieved remarkable success in a range of tasks, from continuous control problems in robotics to playing games like Go and Atari. The improvements seen in these domains have so far been limited to individual tasks, where a separate agent has been tuned and trained for each task. In this work, the researchers explore the challenge of training a single agent on many tasks.
|
Discovering Types for Entity Disambiguation (OpenAI)
A system for automatically figuring out which object is meant by a word by having a neural network decide if the word belongs to each of about 100 automatically-discovered “types” (non-exclusive categories).
|
Introduction to Learning to Trade with Reinforcement Learning
(Disclosure: My own post). The academic Deep Learning research community has largely stayed away from the financial markets. In this post, I’m arguing that training Reinforcement Learning agents to trade in the financial and cryptocurrency markets can be an extremely interesting research problem.
|
|
Lime: Explaining the predictions of any machine learning classifier
This project is about explaining what machine learning models are doing. It currently supports explaining individual predictions for text classifiers and classifiers that act on tables or images. Check out this promo video.
|
DMLab-30 environments
DMLab-30 is a set of environments designed for DeepMind Lab. These environments enable a researcher to develop agents for a large spectrum of interesting tasks either individually or in a multi-task setting. 28 levels are currently released.
|
Building a Deep Neural Net In Google Sheets
An implementation of a Convolutional Neural Network in Google Sheets. The network classifies handwritten digits. A great way to intuitively learn how CNN filters are working.
|
TensorFlow 1.6.0 (RC0) Release
New features include the export of stripped SavedModels from Estimators and FFT support added to XLA CPU/GPU.
|
|
[1802.01548] Regularized Evolution for Image Classifier Architecture Search
The effort devoted to hand-crafting image classifiers has motivated the use of architecture search to discover them automatically. This study employs a regularized version of a popular asynchronous evolutionary algorithm which is compared to the non-regularized form and to a highly-successful reinforcement learning baseline. These models set a new state of the art for CIFAR-10 (mean test error = 2.13%) and mobile-size ImageNet (top-5 accuracy = 92.1% with 5.06M parameters), and reach the current state of the art for ImageNet (top-5 accuracy = 96.2%).
|
[1802.01561] IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Solving a large collection of tasks using a single reinforcement learning agent with a single set of parameters. The authors developed a new distributed agent IMPALA (Importance Weighted Actor-Learner Architecture) that not only uses resources more efficiently in single-machine training but also scales to thousands of machines without sacrificing data efficiency or resource utilization. IMPALA is able to achieve better performance than previous agents with less data, and exhibits positive transfer between tasks as a result of its multi-task approach.
|
[1802.02871] Online Learning: A Comprehensive Survey
This survey aims to provide a comprehensive survey of the online machine learning literature through a systematic review of basic ideas and key principles and a proper categorization of different algorithms and techniques. Online learning can be classified into three major categories: (i) supervised online learning where full feedback information is always available, (ii) online learning with limited feedback, and (iii) unsupervised online learning where there is no feedback available.
|
[1802.00614] Visual Interpretability for Deep Learning: a Survey
This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. The authors focus on convolutional neural networks (CNNs), and the visualization of CNN representations, methods of diagnosing representations of pre-trained CNNs, approaches for disentangling pre-trained CNN representations, learning of CNNs with disentangled representations, and middle-to-end learning based on model interpretability.
|
Did you enjoy this issue?
|
|
|
|
In order to unsubscribe, click here.
If you were forwarded this newsletter and you like it, you can subscribe here.
|
|
|