You are on page 1of 3

Deep Learning

he increase in number and variety of malware samples amplifies the need for
improvement in automatic detection and classification of the malware
variants. Machine learning is a natural choice to cope with this increase,
because it addresses the need of discovering underlying patterns in large-scale
datasets. Nowadays, neural network methodology has been grown to the state
that can surpass limitations of previous machine learning methods, such as
Hidden Markov Models and Support Vector Machines. As a consequence,
neural networks can now offer superior classification accuracy in many
domains, such as computer vision or natural language processing. This
improvement comes from the possibility of constructing neural networks with
a higher number of potentially diverse layers and is known as Deep Learning.

we attempt to transfer these performance improvements to model the


malware system call sequences for the purpose of malware classification. We
construct a neural network based on convolutional and recurrent network
layers in order to obtain the best features for classification. This way we get a
hierarchical feature extraction architecture that combines convolution of n-
grams with full sequential modeling. Our evaluation results demonstrate that
our approach outperforms previously used methods in malware classification,
being able to achieve an average of 85.6% on precision and 89.4% on recall
using this combined neural network architecture.

Deep Learning and Artificial Intelligence (AI) techniques are transforming a


range of sectors from computer vision and natural language processing to
autonomous driving and healthcare. In particular, deep learning

methods achieve great success in many computer vision problems, such as


image classification and object detection. Deep neural networks are very
powerful to capture the hierarchical representation of features in massive

and complex data by adopting multiple layers of non-linear information


processing. Due to the availability of
vast and high-resolution geospatial data and efficient high-performance
computing architectures, deep learning

techniques empower the geospatial system to provide fast and near-human


level perception. For example, recent studies have shown deep learning
techniques coupled with volunteered geographic information (such as

OpenStreetMap data) can accurately extract buildings from satellite imagery


for humanitarian mapping in rural

African areas. Also, deep learning helps assimilate autonomous vehicles and
intelligent transport system by

incorporating a great amount of information gathered by traffic cameras and


sensors. Moreover, deep learning

technology facilitates the discovery of geographic information within


unstructured text data across different languages. There are also many other
applications of deep learning in the domain of GIS, such as the prediction

for spatial diffusion patterns in epidemiology, urban expansion prediction,


and hyperspectral image analysis.

Top Applications of Deep Learning

Self Driving Cars, News Aggregation and Fraud News Detection

Natural Language Processing, Virtual Assistants, Entertainment,

Visual Recognition, Fraud Detection, Healthcare, Personalisations

Detecting Developmental Delay in Children.

Colourisation of Black and White images, Adding sounds to silent movies,

Automatic Machine Translation, Automatic Handwriting Generation,

Automatic Game Playing, Language Translations,

Pixel Restoration, Photo Descriptions,

Demographic and Election Predictions, Deep Dreaming.


Submitted by: Supervised by:

Ali Mahmoud Ali Prof. Dr. Belal Al-Khateeb

Saad Thabit Zgetun

Albara Asaad Mahmoud

Stage:4th morning

Dep: computer science

You might also like