The terrifying faces may look like creatures from a horror movie, but these digital images were actually generated by artificial intelligence (AI). Pix2pix project has unleashed a new tool that analyzes portraits and fills them in with colors and textures using a technique called generative adversarial networks (GANs). During the process, the system determines if its result match the sketch and will keep repeating the generation process until its own passes as'real' – regardless of how nightmarish the results may look. The terrifying faces may look like creatures from a horror movie, but these digital images were actually generated by artificial intelligence (AI). Users are presented with an input box and an output box and are prompted to draw a face in input, select process and in seconds, the AI will reveal its version of the sketch.

Kiva is an online non-profit crowdsouring microfinance platform that raises funds for the poor in the third world. The borrowers on Kiva are small business owners and individuals in urgent need of money. To raise funds as fast as possible, they have the option to form groups and post loan requests in the name of their groups. While it is generally believed that group loans pose less risk for investors than individual loans do, we study whether this is the case in a philanthropic online marketplace. In particular, we measure the effect of group loans on funding time while controlling for the loan sizes and other factors. Because loan descriptions (in the form of texts) play an important role in lenders' decision process on Kiva, we make use of this information through deep learning in natural language processing. In this aspect, this is the first paper that uses one of the most advanced deep learning techniques to deal with unstructured data in a way that can take advantage of its superior prediction power to answer causal questions. We find that on average, forming group loans speeds up the funding time by about 3.3 days.

State-level minimum Bayes risk (sMBR) training has become the de facto standard for sequence-level training of speech recognition acoustic models. It has an elegant formulation using the expectation semiring, and gives large improvements in word error rate (WER) over models trained solely using cross-entropy (CE) or connectionist temporal classification (CTC). sMBR training optimizes the expected number of frames at which the reference and hypothesized acoustic states differ. It may be preferable to optimize the expected WER, but WER does not interact well with the expectation semiring, and previous approaches based on computing expected WER exactly involve expanding the lattices used during training. In this paper we show how to perform optimization of the expected WER by sampling paths from the lattices used during conventional sMBR training. The gradient of the expected WER is itself an expectation, and so may be approximated using Monte Carlo sampling. We show experimentally that optimizing WER during acoustic model training gives 5% relative improvement in WER over a well-tuned sMBR baseline on a 2-channel query recognition task (Google Home).

We present a general framework for training deep neural networks without backpropagation. This substantially decreases training time and also allows for construction of deep networks with many sorts of learners, including networks whose layers are defined by functions that are not easily differentiated, like decision trees. The main idea is that layers can be trained one at a time, and once they are trained, the input data are mapped forward through the layer to create a new learning problem. The process is repeated, transforming the data through multiple layers, one at a time, rendering a new data set, which is expected to be better behaved, and on which a final output layer can achieve good performance. We call this forward thinking and demonstrate a proof of concept by achieving state-of-the-art accuracy on the MNIST dataset for convolutional neural networks. We also provide a general mathematical formulation of forward thinking that allows for other types of deep learning problems to be considered.

We propose a new formulation for pruning convolutional kernels in neural networks to enable efficient inference. We interleave greedy criteria-based pruning with fine-tuning by backpropagation - a computationally efficient procedure that maintains good generalization in the pruned network. We propose a new criterion based on Taylor expansion that approximates the change in the cost function induced by pruning network parameters. We focus on transfer learning, where large pretrained networks are adapted to specialized tasks. The proposed criterion demonstrates superior performance compared to other criteria, e.g. the norm of kernel weights or feature map activation, for pruning large CNNs after adaptation to fine-grained classification tasks (Birds-200 and Flowers-102) relaying only on the first order gradient information. We also show that pruning can lead to more than 10x theoretical (5x practical) reduction in adapted 3D-convolutional filters with a small drop in accuracy in a recurrent gesture classifier. Finally, we show results for the large-scale ImageNet dataset to emphasize the flexibility of our approach.

When it comes to Artificial Intelligence (AI), people's responses vary: from "Terminator and Skynet are coming to kill us all" to "Will the bots take my jobs?" to "Awesome, now I can sit back and do the fun stuff while the bots take care of tedious tasks for me." But there are also misperceptions and misinformation. It's always useful to have a basic grasp of AI, because whether you like it or not, AI is already manifesting in many aspects of our lives. For instance, you can now order Domino's pizzas by talking to your phone. Plus, the pizza giant also says it is moving from a "mobile first" to an "AI first" philosophy.

It is very likely that you've heard all the buzz that has been going lately about the chatbots, and how they're going to revolutionize everything in the coming years, but if you haven't, you must've been hidden in a cave with no internet access at all. Well, fear no more, dear reader, this is (part one of) all you need to know about chatbots. In general terms, a bot is a piece of software that automates a task, but talking specifically about chatbots, we come to the concept of automating an interaction through a conversational UI. Chatbots are a way in which you can automate a written conversation, simulating an interaction between two real human beings. Think of it as a magical black box that understands what you tell it with your daily English (or Spanish, or German, or Mandarin, or whatever) and answers you in the same language, and not in a stream of ones and zeros.

What you should know about deep machine learning and artificial intelligence (AI). Why companies are investing heavily in developing algorithms capable of processing large data-sets. And how such solutions and applications are transforming our world. It looks for tumors that otherwise can't be detected by human eye, composes and plays music of your taste and even drives cars. AI and deep learning is a new technology that is transforming the world.

Imagine being able to use your Apache Spark skills to build and execute deep learning workflows to analyze images or otherwise crunch vast reams of unstructured data. That's the gist behind Deep Learning Pipelines, a new open source package unveiled yesterday by Databricks. Deep Learning Pipelines, which was unveiled at the Spark Summit conference in San Francisco Tuesday, will essentially provide a way to extend the Spark MLlib library to popular deep learning frameworks like TensorFlow and Keras. This will allow Spark users to leverage existing work they've done in MLlib, and to execute deep learning models directly in Spark's existing machine learning library, says Reynold Xin, co-founder and chief architect at Databricks, the commercial outfit behind Apache Spark. "It's a library to integrate essentially all deep learning libraries with Spark to make deep learning substantially easier without having to actually learn about the specifics of deep learning," Xin tells Datanami.

On May 16, OpenAI researchers shared a video of one of their projects along with two papers of importance exploring solutions to three key bottlenecks of current AI development: meta-learning, one-shot learning, and automated data generation. In my previous post, I promised an article dedicated to the fascinating problem of one-shot learning, so here goes. In this video you see a one-arm physical robot stacking cubes on top of each other. Knowing the complex tasks that industrial robots are currently able to perform, if the researcher was not trying to explain what is going on, on many accounts this would be very underwhelming. In controlled environment the task is simple, procedural (hard-coded) approaches have solved this problems already, what is promising and revolutionary is how much the general framework underneath could scale up to multiple, more complex and adaptive behaviors in noisier environments.