Armen Aghajanyan

Learn More
Melanins are widely used in medicine, pharmacology, cosmetics and other fields. Although several technologies for the purification of water-insoluble dioxyphenylalanine (DOPA) melanins have been described, a source of water-soluble melanin is highly desirable. Here we describe an effective procedure for the isolation and purification of water-soluble(More)
Deep neural networks are learning models with a very high capacity and therefore prone to over-fitting. Many regularization techniques such as Dropout, DropConnect, and weight decay all attempt to solve the problem of over-fitting by reducing the capacity of their respective models (Srivastava et al., 2014), (Wan et al., 2013), (Krogh & Hertz, 1992). In(More)
Initialization of parameters in deep neural networks has been shown to have a big impact on the performance of the networks (Mishkin & Matas, 2015). The initialization scheme devised by He et al, allowed convolution activations to carry a constrained mean which allowed deep networks to be trained effectively (He et al., 2015a). Orthogonal initializations(More)
The downfall of many supervised learning algorithms, such as neural networks, is the inherent need for a large amount of training data (Benediktsson et al., 1993). Although there is a lot of buzz about big data, there is still the problem of doing classification from a small data-set. Other methods such as support vector machines, although capable of(More)
Recently, the problem of local minima in very high dimensional non-convex optimization has been challenged and the problem of saddle points has been introduced. This paper introduces a dynamic type of normalization that forces the system to escape saddle points. Unlike other saddle point escaping algorithms, second order information is not utilized, and the(More)
  • 1