In data engineering, augmentation is a process by which we create various transformations of the available data in the ML training dataset. Augmentation task examples are the perturbation of an image in different ways. Augmentation aims at increasing the amount of data input provided to a model to better fit the data into the model ... Read more
Authentication Authentication in computer systems uses application protocols to verify that the identity which is requesting access to a computing system is actually who they say they are. Common authentication protocols are OpenID, NTLM, Kerberos, PAP and CHAP. There is a long list of authentication protocols available, each one being applicable to different systems and ... Read more
Authorization Authorization works right after authentication, in order to grant access and permissions to an identity requesting access to IT resources. The most common authorization protocol is OAuth, now in OAuth 2.0 version. At least one and a resource owner are involved in the authorization process. Authorization works by having an authorization server assign access ... Read more
Azure is Microsoft's public cloud platform, offering a vast range of cloud computing services from its multitude of geographical regions and datacenters. Azure offers all types of cloud services, including IaaS, PaaS and SaaS and is in the top 3 list of global cloud service providers. You can read more details about Azure services and ... Read more
BaaS means Backup As A Service and refers to any managed service which allows for remote backup and recovery of any type of on-premise or cloud workload, including but not limited to:
In machine learning (ML), bias is a concept which is related to errors in the model's predictions, as a results of multiple assumptions and simplifications in the machine learning algorithm. Due to these assumptions, the ML model becomes easy to explain (explainability) but it often misses to capture the complexity inside the training and testing ... Read more
Bias in machine learning is a type of error which occurs when an ML model's estimations are different than the ground truth, i.e what is known (and validated) to be correct.
Caffe is a deep learning framework, which has been developed by Berkeley AI Research (BAIR) and various other contributors. The Caffe official project website is https://caffe.berkeleyvision.org/.
CNN stands for convolutional neural network. It is a type of artificial neural network which is primarily used in artificial intelligence for image processing and computer vision tasks. CNN network architecture comprises an input layer, followed by one or more pairs of convolution and pooling layers connected in series, then followed by fully connected MLP ... Read more
The coefficient of determination (also depicted as R^2) is a calculation of the proportion of the variance in the dependent variable (noted as y) which is explained by a linear regression model. The value of the coefficient of determination can be in the 0..1 range. The coefficient of determination can be calculated by using the ... Read more
A convex function is a function which features a single global minimum, whereas a non-convex functions presents many local minima. A good analysis on the mathematical aspects and mathematical definition of convex and non-convex functions can be found at: https://rumn.medium.com/convex-vs-non-convex-functions-why-it-matters-in-optimization-for-machine-learning-39cd9427dfcc. Some examples of ML algorithms which have restrictions related to convex functions are the following: ... Read more
The loss function (or sometimes called error function) is a function which compares the output of an ML model as compared to the ground truth for a single training example, while the cost function is meant to be calculated over the entire training set (or mini-batch for mini-batch gradient descent).
A central processing unit (CPU) is a complex electronic circuit which performs all numerical, logic, IO and control computations inside a computer. There are generally two types of CPUs, ie reduced instruction set computers (RISC) and Complex Instruction Set Computers (CISC). There are also other similar circuits to a CPU, with a more specialized scope ... Read more
In machine learning (ML), cross validation is a method in which the data scientists perform an evaluation of an ML model's performance on unlabelled data, i.e. data which the ML model has not seen before. In the method of cross validation, the data which is available in the dataset is split into multiple subsets. One ... Read more
Desktop As A Service (VDI or Hosted Shared Desktops) or Diagnostics As A Service. For Diagnostics as a service, read the following Microsoft article for more details.https://azure.microsoft.com/en-in/blog/daas/.
Data lineage is part of responsible AI and it refers to all procedures related to tracking the origin, transformation, and usage of data throughout its lifecycle in machine learning. This ensures a Privacy by Design ML model.
Definition of DCOM The Microsoft Distributed Component Object Model (DCOM) protocol is used to expose application objects via remote procedure calls (RPCs). DCOM has extensions layered on top of the Remote Procedure Call extensions. Refer to the following Microsoft article for more details on DCOM: https://docs.microsoft.com/en-us/openspecs/windows_protocols/ms-dcom/4a893f3d-bd29-48cd-9f43-d9777a4415b0.
DDOS DDOS stands for distributed denial-of-service attack (DoS attack). It uses similar approach to Denial of Service (DOS) but in this case, the DOS cyber attack is distributed from numerous source networks.
Design patterns are patterns which are applied in the design of software and/or infrastructure systems, aiming to optimize the systems' functional (operations and application or infrastructure features and services) and non-functional characteristics (e.g. performance, reliability, redundancy, security). Design patterns can be divided in the following major categories: Software design patterns. This category includes devops design ... Read more
Dioptra is a software test platform for assessing the trustworthy characteristics of artificial intelligence (AI). Dioptra excels in the area of Adversarial Machine Learning (AML). More details can be found in the official project web site at: https://pages.nist.gov/dioptra/index.html.