In today's day and age when almost every industry has an online presence with users interacting in online marketplaces, personalized recommendations have become quite important. Traditionally, the problem of collaborative filtering has been tackled using Matrix Factorization which is linear in nature. We extend the work of [11] on using variational autoencoders (VAEs) for collaborative filtering with implicit feedback by proposing a hybrid, multi-modal approach. Our approach combines movie embeddings (learned from a sibling VAE network) with user ratings from the Movielens 20M dataset and applies it to the task of movie recommendation. We empirically show how the VAE network is empowered by incorporating movie embeddings. We also visualize movie and user embeddings by clustering their latent representations obtained from a VAE.

Alejandro Saucedo (Founder @ Exponential Technologies) and Donald Whyte (Software Engineer @ Engineers Gate) @ Moscow Python Conf 2017 "There is a lot of hype about deep learning and everything AI, however behind all the noise there is a set of solid concepts and algorithms that have massive potential if used in the right way and with the right data. In this talk we will provide you with the key concepts you will need to build a solid understanding around the core of Machine Learning. We will also cover key Deep Learning concepts and examples using Tensorflow that will help you understand the real potential of Deep Learning in practical applications. This talk will provide a theoretical overview that will then be put in practice in the Deep Learning workshop". Slides: https://conf.python.ru/python-ai-all-... Note: On 7.37 - 7.47 Alejandro says: "The hard part is how do we learn the hyperparameters of the function itself m and c, that is what ML is about.

Today, Artificial Intelligence (AI) and Machine Learning (ML) are two popular terms that tech companies cannot stop talking about. Everyone from Google and Microsoft, to Apple, Samsung and Amazon are going big on AI. Besides smartphones, smart speakers, voice assistants, apps, connected cars, security surveillance, healthcare and customer support are other areas where AI is used. Machine Learning (and deep learning) has been going on for years, and now with the data that exists, tech companies are putting it to the best use. On device machine learning combined with artificial intelligence can help in anticipating things in advance. But while you may not know, AI and ML can be very helpful in customer service too.

On July 9th, our team hosted a live webinar--Scalable End-to-End Deep Learning using TensorFlow and Databricks--with Brooke Wenig, Data Science Solutions Consultant at Databricks and Sid Murching, Software Engineer at Databricks. In this webinar, we walked you through how to use TensorFlow and Horovod (an open-source library from Uber to simplify distributed model training) on the Databricks Unified Analytics Platform to build a more effective recommendation system at scale. If you missed the webinar, you can view it now as well download the slides here. If you'd like free access Databricks Unified Analytics Platform and try our notebooks on it, you can access a free trial here. Toward the end, we held a Q&A, and below are all the questions and their answers.

Alzheimer's disease affects millions of people each year. According to the Alzheimer's Association, it's the 6th leading cause of death in the United States, killing more seniors than breast cancer and prostate cancer combined. It's also expensive -- early diagnosis could save an estimated $7.9 trillion in medical and care costs. Researchers at Unlearn.AI, a startup that designs software tools for clinical research, think that artificial intelligence has a valuable role to play in personalizing diagnosis and treatment. In a paper ("Using deep learning for comprehensive, personalized forecasting of Alzheimer's Disease progression") published on the preprint server Arvix.org,

One popular test, called Raven's Progressive Matrices, features several rows of images with the final row missing its final image. It's up to the test taker to choose the image that should come next based on the pattern of the completed rows. The test doesn't outright tell the test taker what to look for in the images -- maybe the progression has to do with the number of objects within each image, their color, or their placement. It's up to them to figure that out for themselves using their ability to reason abstractly. To apply this test to AIs, the DeepMind researchers created a program that could generate unique matrix problems.

Can machines learn to reason abstractly? That's the subject of a new paper from Google subsidiary DeepMind titled "Measuring abstract reasoning in neural networks," which was presented at the International Conference on Machine Learning in Stockholm, Sweden this week. The researchers define abstract reasoning as the ability to detect patterns and solve problems on a conceptual level. In humans, they note, verbal, spatial, and mathematical reasoning can be measured empirically with tests that task subjects with teasing out the relationships between shape positions and line colors. "Unfortunately, even in the case of humans, such tests can be invalidated if subjects prepare too much, since test-specific heuristics can be learned that shortcut the need for generally applicable reasoning," the researchers explained. "This potential pitfall is even more acute in the case of neural networks, given their striking capacity for memorization."

Conservation group Snapshot Serengeti has been collecting data for years using its motion-sensor "camera traps," which take photos of wild animals without disturbing them. Using AI, researchers have developed a new way to make this monitoring more accurate and efficient. Collaborators from Harvard, Oxford, the University of Minnesota, and Auburn University compiled images with descriptions and labels manually entered by humans. They then used deep learning to train a computer to correctly identify factors like species, number of animals, and types of behavior in images captured by the camera traps. Categorizing these photos manually requires a significant amount of time and resources, with most of the work currently done by volunteers.

As our day by day lives turn out to be progressively interwoven with a wide range of innovation, once in a while it shows up as if the future is already here. Nonetheless, technology keeps on developing, and Artificial Intelligence (AI) has taken the center stage for this talk. Maintained by numerous path forward, AI keeps on holding the public's creative imagination on what the future could be. This conviction is propelled further by advancements, like Amazon's Alexa, Netflix's recommendation framework, and SnapChat's filters– all are the excellent examples of AI entering the private domain of the people. Deep learning is a data learning model that has recently enhanced the prediction accuracy of longstanding benchmarks.

To train the AI, Morrison says that the company first recruited 500 people to record their perceptual reactions on a large set of banner ads. Based on their eye movements, the company could detect which ads caught viewers' attention and which ad didn't, rating each ad on a scale from 0 to 100. The company used that dataset to train a deep learning model built on top of an existing AI model, which had previously been trained with millions of images. Right now, EyeQuant can't cite specific reasons why the AI can be so accurate in its predictions. "We'd like to be able to isolate specific reasons for why one ad works better than another, or even to automatically generate eye-catching banners," says A.I. Engineer Peli Teloni, but right now they can only speculate why.