When I started my first job out of college, I thought I knew a fair amount about machine learning. I had done two internships at Pinterest and Khan Academy building machine learning systems. I spent my last year at Berkeley doing research in deep learning for computer vision and working on Caffe, one of the first popular deep learning libraries. After I graduated, I joined a small startup called Cruise that was building self-driving cars. Now I'm at Aquarium, where I get to help a multitude of companies deploying deep learning models to solve important problems for society.

TalkingData is a data intelligence service provider that offers data products and services to provide businesses insights on consumer behavior, preferences, and trends. One of TalkingData's core services is leveraging machine learning and deep learning models to predict consumer behaviors (e.g., likelihood of a particular group to buy a house or a car) and use these insights for targeted advertising. For example, a car dealer will only want to show their ads to customers who the model predicts are most likely to buy a car in the next three months. Initially, TalkingData was building an XGBoost model for these types of predictions, but their data science team wanted to explore whether deep learning models could have a significant performance improvement for their use case. After experimentation, their data scientists built a model on PyTorch, an open source deep learning framework, that achieved a 13% improvement on recall rate.

Every organization wants to infuse the power of AI in its business. In this second of two parts we'll explore the productivity, performance and cost considerations that should be weighed when deploying deep learning at scale in the enterprise, and how to avoid the pitfalls of short-term decisions that can negatively impact your long term AI strategy.

Deep learning is a machine learning technique used to solve complex problems related to image recognition, natural language processing, and more. It requires both massive amounts of data and computational power. The compute problem has been solved largely by GPUs, which have become essential for making deep learning performant. GPUs have reduced the time required to train models from weeks to days. Most training tasks can be accomplished by building your own box.

In August, 2016, Intel is bolstering its artificial intelligence efforts by acquiring Nervana Systems for 400 million, a two-year-old startup considered among the leaders in developing machine learning technology. In a video, Nervana's Naveen Rao discussed deep learning, a form of machine learning loosely inspired by the brain. Naveen explores the benefits of deep learning over other machine-learning techniques, recent advances in the field, the deep learning workflow, challenges in developing and deploying deep learning-based solutions, and the need for standardized tools for building and scaling deep learning solutions. Convolutional Neural Nets are the main model. They are good for vision systems.