Month: November 2018

William Vorhies provides us a negative (and necessary) look at the current state of Deep Learning solutions:

Reinforcement Learning (RL) is arguably the hottest research area in AI today because it appears RL can be adapted to any problem that has a well-defined reward function.  That encompasses game play, robotics, self-driving cars, and frankly pretty much else in machine learning.

Within RL, the hottest research area is Deep RL which means using a deep neural net as the ‘agent’ in the training.  Deep RL is seen as the form of RL with the most potential to generalize over the largest number of cases and perhaps the closest we’ve yet come to AGI (artificial general intelligence).

Importantly, Deep RL is also the technique used to win at Alpha Go which brought it huge attention.

The problem is, according to Alex Irpan, a researcher on the Google Brain Robotics team that about 70% of the time they just don’t work.

Alex has written a very comprehensive article critiquing the current state of Deep RL, the field with which he engages on a day-to-day basis.  He lays out a whole series of problems and we’ve elected to focus on the three that most clearly illustrate the current state of the problem with notes from his work.

Vorhies is not unduly negative and is optimistic in the medium to long term, but he is right in noting that there is a lot of work yet to do in this field.

Xindian Long explains some of the techniques which convolutional neural networks use to discern objects in images:

Can we do object detection in a smart way by only looking at some of the windows? The answer is yes. There are two approaches to find this subset of windows, which lead to two different categories of object detection algorithms.

1. The first algorithm category is to do region proposal first. This means regions highly likely to contain an object are selected either with traditional computer vision techniques (like selective search), or by using a deep learning-based region proposal network (RPN). Once you have gathered the small set of candidate windows, you can formulate a set number of regression models and classification models to solve the object detection problem. This category includes algorithms like Faster R-CNN[1], R_FCN[2] and FPN-FRCN[3]. Algorithms in this category are usually called two-stage methods. They are generally more accurate, but slower than the single-stage method we introduce below.
2. The second algorithm category only looks for objects at fixed locations with fixed sizes. These locations and sizes are strategically selected so that most scenarios are covered. These algorithms usually separate the original images into fixed size grid regions. For each region, these algorithms try to predict a fixed number of objects of certain, pre-determined shapes and sizes. Algorithms belonging to this category are called single-stage methods. Examples of such methods include YOLO[4], SSD[5] and RetinaNet[6]. Algorithms in this category usually run faster but are less accurate. This type of algorithm is often utilized for applications requiring real-time detection.

We’ll discuss two common object detection methods below in more detail.

This is a high-level explanation with no code, but it does a good job of describing at that level what is going on.