Editor's note: This is a followup to the recently published part 1 and part 2. You may want to check them out before moving forward. In the last article we will talk about basics of deep learning from the lens of Convolutional Neural Nets. In this article we will focus -- basic deep learning using Keras and Theano. We will do 2 examples one using keras for basic predictive analytics and other a simple example of image analysis using VGG.

Google has made the app open-source so any developer can adopt it. It can perform chores like object detection, face attribute recognition, fine-grained classification (recognizing a dog-breed, for instance) and landmark recognition. The tech is part of TensorFlow, Google's deep learning model that recently shrunk down to mobile size in a new version called TensorFlow Lite. MobileNets is not one-size-fits-all, as Google has actually built 16 pre-trained models "for use in mobile projects of all sizes." The larger the model, the better it is at recognizing landmarks, faces or doggos, with the most CPU-intensive ones hitting scores of between 70.7 and 89.5 percent accuracy.

AlphaGo and self-driving cars are amazingly clever, but neither represents a very big leap toward general artificial intelligence. Fortunately, some AI researchers are developing ways of broadening machine intelligence. The researchers at DeepMind, which created the champion Go-playing robot AlphaGo, are working on an approach that could prove significant in the quest to make machines as intelligent as we are. In two papers published this week and reported by New Scientist, researchers at the Alphabet subsidiary describe efforts to teach computers about relational reasoning, a cognitive capability that is foundational to human intelligence. Simply put, relational reasoning is the ability to consider relationships between different mental representations, such as objects, words, or ideas.

The fundamental principal of Learning is something that is so inherently easy to understand it ends up a challenge to express (almost like the problem of explaining the concept of Left and Right). We Learn every day, hour, and second we complete any form of activity. Even in our daily commute any individual will continuously update, correct, analyze and decipher patterns and situations. In order to understand and adapt to our surroundings we analyze and dissect situations daily. From crossing the road at a certain intersection to changing cashier desk in the supermarket we employ learning techniques continuously.

Deep Learning is now of the hottest trends in Artificial Intelligence and Machine Learning, with daily reports of amazing new achievements, like doing better than humans on IQ test. In 2015 KDnuggets Software Poll, a new category for Deep Learning Tools was added, with most popular tools in that poll listed below. I haven't used all of them, so this is a brief summary of these popular tools based on their homepages and tutorials. Theano and Pylearn2 are both developed at University of Montreal with most developers in the LISA group led by Yoshua Bengio. Theano is a Python library, and you can also consider it as a mathematical expression compiler.

Actually I've known about MXnet for weeks as one of the most popular library / packages in Kaggler, but just recently I heard bug fix has been almost done and some friends say the latest version looks stable, so at last I installed it. I think that the most important feature of MXnet is its implementation of not only Deep Neural Network (DNN) but also Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) in R, because as far as I've known there has been no R packages implementing CNN (and/or RNN). In the original post of my blog, I tried a CNN {mxnet} R package with a short version of MNIST handwritten digit datasets whose maximum accuracy may be less than 0.98 for its small sample size. As a result, CNN of {mxnet} performed accuracy 0.976: this is better than Random Forest (0.951), Xgboost (0.953) or DNN by {h2o} (0.962). MXnet is a framework distributed by DMLC, the team also known as a distributor of Xgboost.

Three Udacity students each took different approaches to vehicle detection and tracking -- some using deep learning and others using standard computer vision. Ivan has a terrific writeup of how to use deep learning for vehicle detection. He builds a model based on Faster-RCNN, but smaller and faster. Martijn uses a HOG and SVM approach to build a vehicle detection pipeline. He encountered some issues with noise and finds a creative solution.

AI systems continue to get increasingly powerful, but still need far too much hand-holding by their human masters. New research from DeepMind and OpenAI suggests a mere nudge here and there at the outset can be enough to help artificial intelligence accomplish tricky tasks. The team set up a series of experiments in which human participants were given two short clips of an AI's approach to a task. They were then asked to make a snap judgement about which clip appeared to show more promising progress – but without the AI being aware of the desired outcome of the task. One scenario involved the AI learning to play Space Invaders, another involved a virtual robot learning to do backflips.

The robot Shimon composes and performs his first deep learning driven piece. A recurrent deep neural network is trained on a large database of classical and jazz music. Based on learned semantic relationships between musical units in this dataset, Shimon generates and performs a new musical piece.

The Institute of Formal and Applied Linguistics (UFAL) is seeking a candidate for a one-year post-doc position in the area of neural machine translation (NMT). The exact topic will be determined based on the candidate's interests, e.g. A PhD degree in computational linguistic, artificial intelligence or a related field is required. Experience with neural MT, Linux and cluster environment (SGE), and/or general deep learning and GPU computation is a bonus.