Know what you don't know: Tools to understand uncertainty in DL

Know what you don't know: Tools to understand uncertainty in DL

In this "Know what you don't know: Tools to understand uncertainty in Deep Learning", we want to bridge the gap between practical methods for Deep Learning and Bayesian Inference in a practical setting. We will start by introducing common problems in machine learning systems that arise from the lack of understanding of how uncertain models are when given specific inputs. This causes limitations on applications that need robust solutions and can impact people lives, such as healthcare, financial trading, and autonomous vehicles.

In this talk, we want to bridge the gap between practical methods for Deep Learning and Bayesian Inference in a practical setting.

As motivation, we will start by introducing common problems in machine learning systems that arise from the lack of understanding of how uncertain models are when given specific inputs. This causes limitations on applications that need robust solutions and can impact people lives, such as healthcare, financial trading, and autonomous vehicles.

We will present Bayesian Neural Networks and cover the fundamentals of Bayesian Inference. Dropout layers and other stochastic regularization techniques, when viewed in the lens of BNNs, offer us out-of-the-box tools to measure uncertainty that we can implement with little or no cost to existing architectures.

To close, we will go over real-life applications of these techniques down to some code snippets. Better estimation of what the model doesn't know enables faster explore-exploit tradeoffs in reinforcement learning problems and more efficient use of annotations through active sampling.

Artificial Intelligence (AI) Tutorial - Getting started with AI

Artificial Intelligence (AI) Tutorial - Getting started with AI

Artificial Intelligence (AI) Tutorial - Getting started with Artificial Intelligence. In this Artificial Intelligence tutorial you will learn end to end about AI and it's vast domain. So this AI tutorial for beginners is an exhaustive tutorial for you to get started with AI.

In this Artificial Intelligence (AI) tutorial you will learn end to end about AI and it's vast domain. So this AI tutorial for beginners is an exhaustive tutorial for you to get started with AI.

Deep Learning vs Machine Learning: Which is the Best Choice for AI?

Deep Learning vs Machine Learning: Which is the Best Choice for AI?

Deep Learning vs. Machine Learning: You'll learn how the two concepts compare and how they fit into the broader category of Artificial Intelligence. During this demo we will also describes how deep learning can be applied to real-world scenarios such as fraud detection, voice and facial recognition, sentiment analytics, and time series forecasting.

This episode helps you compare deep learning vs. machine learning. You'll learn how the two concepts compare and how they fit into the broader category of artificial intelligence. During this demo we will also describes how deep learning can be applied to real-world scenarios such as fraud detection, voice and facial recognition, sentiment analytics, and time series forecasting.

An Introduction to Artificial Intelligence (AI)

An Introduction to Artificial Intelligence (AI)

In this Introduction to Artificial Intelligence and in computer science, artificial intelligence (AI), sometimes called machine intelligence. Before leading to the meaning of artificial intelligence let understand what is the meaning of the Intelligence - Intelligence. Colloquially, the term "artificial intelligence" is often used to describe machines (or computers) that mimic "cognitive" functions that humans associate with the human mind, such as "learning" and "problem solving"

Before leading to the meaning of artificial intelligence let understand what is the meaning of the Intelligence - Intelligence: The ability to learn and solve problems. This definition is taken from webster’s Dictionary.

The most common answer that one expects is “to make computers intelligent so that they can act intelligently!”, but the question is how much intelligent? How can one judge the intelligence?

…as intelligent as humans. If the computers can, somehow, solve real-world problems, by improving on their own from the past experiences, they would be called “intelligent”.
Thus, the AI systems are more generic(rather than specific), have the ability to “think” and are more flexible.

Intelligence, as we know, is the ability to acquire and apply the knowledge. Knowledge is the information acquired through experience. Experience is the knowledge gained through exposure(training). Summing the terms up, we get artificial intelligence as the “copy of something natural(i.e., human beings) ‘WHO’ is capable of acquiring and applying the information it has gained through exposure.”

Intelligence is composed of:
  • Reasoning
  • Learning
  • Problem Solving
  • Perception
  • Linguistic Intelligence

Many tools are used in AI, including versions of search and mathematical optimization, logic, methods based on probability and economics. The AI field draws upon computer science, mathematics, psychology, linguistics, philosophy, neuro-science, artificial psychology and many others.

Need for Artificial Intelligence
  1. To create expert systems which exhibit intelligent behavior with the capability to learn, demonstrate, explain and advice its users.
  2. Helping machines find solutions to complex problems like humans do and applying them as algorithms in a computer-friendly manner.

Applications of AI include Natural Language Processing, Gaming, Speech Recognition, Vision Systems, Healthcare, Automotive etc.

An AI system is composed of an agent and its environment. An agent(e.g., human or robot) is anything that can perceive its environment through sensors and acts upon that environment through effectors. Intelligent agents must be able to set goals and achieve them. In classical planning problems, the agent can assume that it is the only system acting in the world, allowing the agent to be certain of the consequences of its actions. However, if the agent is not the only actor, then it requires that the agent can reason under uncertainty. This calls for an agent that cannot only assess its environment and make predictions but also evaluate its predictions and adapt based on its assessment. Natural language processing gives machines the ability to read and understand human language. Some straightforward applications of natural language processing include information retrieval, text mining, question answering and machine translation. Machine perception is the ability to use input from sensors (such as cameras, microphones, sensors etc.) to deduce aspects of the world. e.g., Computer Vision. Concepts such as game theory, decision theory, necessitate that an agent be able to detect and model human emotions.

Many times, students get confused between Machine Learning and Artificial Intelligence, but Machine learning, a fundamental concept of AI research since the field’s inception, is the study of computer algorithms that improve automatically through experience. The mathematical analysis of machine learning algorithms and their performance is a branch of theoretical computer science known as a computational learning theory.

Stuart Shapiro divides AI research into three approaches, which he calls computational psychology, computational philosophy, and computer science. Computational psychology is used to make computer programs that mimic human behavior. Computational philosophy is used to develop an adaptive, free-flowing computer mind. Implementing computer science serves the goal of creating computers that can perform tasks that only people could previously accomplish.

AI has developed a large number of tools to solve the most difficult problems in computer science, like:
  • Search and optimization
  • Logic
  • Probabilistic methods for uncertain reasoning
  • Classifiers and statistical learning methods
  • Neural networks
  • Control theory
  • Languages

High-profile examples of AI include autonomous vehicles (such as drones and self-driving cars), medical diagnosis, creating art (such as poetry), proving mathematical theorems, playing games (such as Chess or Go), search engines (such as Google search), online assistants (such as Siri), image recognition in photographs, spam filtering, prediction of judicial decisions[204] and targeting online advertisements. Other applications include Healthcare, Automotive
Finance, Video games etc

Are there limits to how intelligent machines – or human-machine hybrids – can be? A superintelligence, hyperintelligence, or superhuman intelligence is a hypothetical agent that would possess intelligence far surpassing that of the brightest and most gifted human mind. ‘’Superintelligence’’ may also refer to the form or degree of intelligence possessed by such an agent.

**References: **https://en.wikipedia.org/wiki/Artificial_intelligence