Andrew Ng Unveils Deeplearning.ai – New DL Courses on Coursera
Andrew Ng, one of the top minds in deep learning, loves teaching. And so, the Stanford University professor decided toContinue Reading
Category: Research
Technical review of the newest machine intelligence research.
Deep Learning-Based Food Calorie Estimation Method in Dietary Assessment
Although food packaging comes with nutrition labels, it’s still not convenient for people to reference. Thus, scientists started to use machine learning algorithms in computer vision to help people determine the caloric value in the food they eat.
Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models
The paper proposes a hybrid neural machine translation model concerning both words and characters, which mainly contributes to the translation of rare or unknown words.
PixelGAN Autoencoders
PixelGAN is an autoencoder for which the generative path is a convolutional autoregressive neural network on pixels, conditioned on a latent code, and the recognition path uses a generative adversarial network (GAN) to impose a prior distribution on the latent code.
Learning to Map Vehicles into Bird’s Eye View
This paper presents a deep learning architecture to map the vehicle detection in the frontal view onto a bird’s eye view of the road scene, while preserving the size and direction of the moving vehicle.
Generalizing and Hybridizing Count-based and Neural Language Model
This paper demonstrates a framework called Mixture Of Distribution Language Models (MODLMs), which provides a single mathematical framework that encompasses several widely used classes of LMs.
Kullback-Leibler Divergence Explained
Minimization of the KL-divergence can be thought of as maximizing the likelihood ratio, which appears in numerous applications.
Apple is in a Dilemma on iPhone’s 10-year-old Birthday
Apple is confused about what its next big thing will be.
Navigating Intersections with Autonomous Vehicles using Deep Reinforcement Learning
One crucial standard in measuring autonomous vehicles is whether the autonomous vehicles can go through intersections with no signals. In this paper, the authors provide us with a new strategy of using Deep Reinforcement Learning.
Applying Data Science to Robotics
In his blog post “How Data Science Apply to Robotics” on Data Science Central, Dr. Ammar A. Raja points out that there are two major problems scientists have encountered while applying data science to robotics.
Applying Multinomial Naive Bayes to NLP Problems: A Practical Explanation
Bayes’ Theorem is useful for dealing with conditional probabilities, since it provides a way for us to reverse them.
Email Category Prediction
By accurately predicting the category of an email, we can better extract useful information from it according to its corresponding templates.
A Rational Analysis of Curiosity
Curiosity is related to the field of intrinsic motivation, and is recognized as a factor in a wide range of human endeavour.
Massive Exploration of Neural Machine Translation Architectures
Although no innovations for the NMT architecture was introduced, the authors claim that a classic NMT baseline system with carefully tuned hyperparameters can still achieve comparable result to the state-of-the-art.
Exploiting Source-side Monolingual Data in Neural Machine Translation
Instead of exploring target-side monolingual data for NMT, the author of this paper proposes two novel methods for source-side monolingual data exploration.
Giving Robots a Sense of Touch
The rubber on GelSight sensor will conform to any object pressed against it, resulting in the reflective lights on the metallic paint to vary according to different materials and shapes.
Appearance-Based Gaze Estimation in the Wild
Multimodal convolutional neural networks for appearance-based gaze estimation that significantly outperforms state-of-the-art methods in the most challenging cross-dataset evaluation
Using Human Brain Activity to Guide Machine Learning
Instead of investigating what steps the brain takes to process information, the authors of this paper link brain activity directly to the learning process.
Gary Marcus: The Road to Artificial General Intelligence
Gary Marcus the Professor of Psychology at New York University, CEO and Founder of Geometric Intelligence, speaks at GMIS 2017.
Understanding the Mechanisms of Deep Transfer Learning for Medical Images
This paper systematically studies how a convolutional neural network, trained on ImageNet for image classification tasks, works on medical images – or more precisely on ultrasound images – for the “Kidney Detection” problem.
Tensorflow Programs and Tutorials
This repository did some toy experiments based on Tensorflow in order to introduce some deep learning concepts which are used for image recognition and language modeling.
Deep Learning with Dynamic Computation Graphs
Google introduced a new algorithm: ‘Dynamic Batching’, and developed a Tensorflow-based library called ‘TensorFlow Fold’, which solved the DCGs problem in both theoretical and empirical fields.
Conversational Systems: A General Review
How can we communicate with “super intelligent” robots? The answer lies in conversational systems.
Global AI Hackathon in Toronto
On June 23-24, the first Global Artificial Intelligence Hackathon took place in Toronto at University of Toronto, alongside 14 otherContinue Reading
A Survey of Question Answering for Math and Science Problem
Overview of the ways to make a machine smart enough to pass the standardized math and science test.
L2-constrained Softmax Loss for Discriminative Face Verification
Softmax loss has become a standard build-in loss function for a lot of mathematical tools like TensorFlow, Torch and Caffe. It is mainly used for classification and has its advantages and disadvantages, the latter of which is the focus of this paper.
Deep Learning Paper Sparks Online Feud!
A tweet from Google DeepMind’s Nenad Tomasev, concerning a paper from the prestigious Montreal Institute for Learning Algorithms has sparked a well-known natural language processing expert Yoav Goldberg to tweet back: “…I really dislike this work.”
Failures of Deep Learning
In 2015, Anh Nguyen published a paper in CVPR that identified a limit in computer vision, where you can fool a deep neural network (DNN) by changing an image in a way that’s imperceptible to humans, but can cause the DNN to label the image as something else entirely.
Epic’s Tim Sweeney: Deep Learning A.I. Will Open New Frontiers in Game Design
Tim Sweeney predicts that video game companies will ultimately utilize advanced AI techniques when the VR/AR games (or so-called “The Metaverse” games) become popular, due to advancements of cameras and displays
How to Teach Machines to Think Like Humans
Google’s DeepMind introduced its Relation Network (RN) module and a Visual Interaction Network (VIN) that achieved superhuman performance in specific tests by employing a different type of reasoning concerning objects and physical interactions.
Does Fitness Data Make the Average Person Healthier?
With these handy wearable gadgets, we can now track every aspect of our health and fitness. But are they actually making a difference to the average person’s well being?
Adversarial Generator-Encoder Networks
New autoencoder-like generative network, called Adversarial Generator-Encoder Networks (AGE Network), does not have any discriminators, which makes the entire architecture much simpler than some recently-proposed GANs, but with nearly the same-level performance
Customer Success with Machine Learning (Google Cloud NEXT’17)
The reason why TensorFlow is so widely used is due to its automatic derivation of functions and distributed computing capability. This increase in interest can also be found in commercial applications.
Exploring Sparsity in Recurrent Neural Networks
In order to deploy Recurrent Neural Networks (RNNs) efficiently, we propose a technique to reduce the parameters of a network by pruning weights during the initial training of the network.
C2 Montreal – Master Class with Yoshua Bengio: Know The Basics
Professor Bengio delivered the “Fundamentals of AI” masterclass to a cross-industry audience at C2 event in Montreal, Canada.
Word2vec: Google’s New Leap Forward on the Vectorized Representation of Words
Word2vec is an open source tool developed by a group of Google researchers led by Tomas Mikolov in 2013. It describes several efficient ways to represent words as M-dimensional real vectors, also known as word embedding, which is of great importance in many natural language processing applications
Basics of Computational Reinforcement Learning
Intelligent behavior arises from the actions of an individual seeking to maximize its received reward signals in a complex and changing world”. Meanwhile, reinforcement learning is the way to realize AI.
Visual Attribute Transfer through Deep Image Analogy
Researchers from Microsoft Research Asia and Shanghai Jiaotong University have recently published a paper on transferring visual attributes of images using a new technique called Deep Image Analogy.
25 Tweets to Know You: A New Model to Predict Personality with Social Media
In order to provide personalized ads, tech giants such as Google and Facebook are trying to abstract their users’ personality from their posts on social media. Hence, it is essential for social networking applications to predict personality from written text.
How a Deep Neural Network Trained with End-to-End Learning Steers a Car
A practical way to make an autonomous vehicle is not by programming a car to drive in any environment, but by showing the car how to drive and make the car learn by itself. NVIDIA created a system of this kind, named PilotNet.