AI News, Limitations of Deep Learning in AI Research artificial intelligence

ICS Events

Date: Thursday, March 14 Time: 1:30 p.m.–3:00 p.m. Location: 233B HUB-Robeson Center Artificial intelligence (AI) is often claimed to have the promise of transforming and possibly taking over our society.

In an effort to provide context to artificial intelligence’s power and limitations, the talk will highlight the basics of implementing AI into actual problems.

He is also graduate professor of computer science and engineering, courtesy professor of supply chain and information systems, and director of the intelligent systems research laboratory.


Machine learning and radiology are rapidly gaining joint momentum as an interdisciplinary research field.

Four distinguished speakers from areas covering radiology, machine learning and medical image computing will provide a realistic assessment of where we are, and offer their views about most directions that will have advance both fields having an impact on research in novel biomarkers, and clinical applications.

Next Generation, Artificial Intelligence and Machine Learning

Recently deep learning, a new term that describes a set of algorithms that use a neural network as an underlying architecture, has generated many headlines.

Deep learning became more usable in recent years due to the availability of inexpensive parallel hardware (GPUs, computer clusters) and massive amounts of data.

Although deep learning garners much attention, people fail to realize that deep learning has inherent restrictions which limit its application and effectiveness in many industries and fields.

In mission critical applications, such as medical diagnosis, airlines, and security, people must feel confident in the reasoning behind the program, and it is difficult to trust systems that does not explain or justify their conclusions.

For example, in vision classification, slightly changing an image which was once correctly classified in a way that is imperceptible to the human eye can cause a deep neural network to label the image as something else entirely.

The major reason that data mining has attracted attention is due to the wide availability of vast amounts of data, and the need for turning such data into useful information and knowledge.

The knowledge gained can be used for applications ranging from risk monitoring, business management, production control, market analysis, engineering, and science exploration.

decision tree is a flow-chart-like tree structure where each node denotes a test on an attribute value, each branch represents an outcome of the test, and each tree leaf represents a class or class distribution.

The data mining process consists of an iterative sequence of the following steps: GIGO (garbage in garbage out) is almost always referenced with respect to data mining, as the quality of the knowledge gained through data mining is dependent on the quality of the historical data.

limitation of data mining is that it only extracts knowledge limited to the specific set of historical data, and answers can only be obtained and interpreted with regards to previous trends learned from the data.

Rather than relying on a domain expert to write the rules or make associations along generalized relationships between problem descriptors and conclusions, a CBR system learns from previous experience in the same way a physician learns from his patients.

A CBR system will create generic cases based on the diagnosis and treatment of previous patients to determine the disease and treatment for a new patient.

A genetic algorithm operates through a cycle of three stages: Genetic algorithms provide various benefits to existing machine learning technologies such as being able to be used by data mining for the field/attribute selection, and can be combined with neural networks to determine optimal weights and architecture.

We will begin by listing the most important limits of legacy machine learning techniques and will then describe how the next generation of artificial intelligence based on smart-agents overcomes these limitations. As

Most importantly, they lack the capacity for: Personalization: To successfully protect and serve customers, employees, and audiences we must know them by their unique and individual behavior over time and not by static, generic categorization.

In network security, we know every day dozens of new malware programs with ever more sophisticated methods of embedding and disguising themselves appear on the internet.

The problem is it is often easy for hackers to reverse engineer the patch and therefore another defect is found and exploited within hours of the release of the given patch.

It must be able to change its parameters to thrive in new environments, learn from each individual activity, respond to various situations in different ways, and track and adapt to the specific situation/behavior of every entity of interest over time.

In a financial portfolio management system, a multi-agent system consist of smart agents that cooperatively monitor and track stock quotes, financial news, and company earnings reports to continuously monitor and make suggestions to the portfolio manager.

Instead, smart agents create profiles specific to each entity and behave according to their goals, observations, and the knowledge that they continuously acquire through their interactions with other smart agents.

Each Smart agent pulls all relevant data across multiple channels, irrespectively to the type or format and source of the data, to produce robust virtual profiles.

Since they focus on updating the profile based on the actions and activities of the entity, they store only the relevant information and intelligence rather than storing the raw incoming data they are analyzing, which achieves enormous compression in storage.

This distributed architecture allows lightning speed response times (below 1 millisecond) on entry level servers as well as end-to-end encryption and traceability.

Yann LeCun - Power & Limits of Deep Learning

Yann LeCun is Director of AI Research at Facebook, and Silver Professor of Dara Science, Computer Science, Neural Science, and Electrical Engineering at ...

The Future of Deep Learning Research

Back-propagation is fundamental to deep learning. Hinton (the inventor) recently said we should "throw it all away and start over". What should we do?

The Deep End of Deep Learning | Hugo Larochelle | TEDxBoston

Artificial Neural Networks are inspired by some of the "computations" that occur in human brains—real neural networks. In the past 10 years, much progress has ...

AI’s Impact Education, Training, and Learning: Potential and Limitations

From the November 13th 2017 Symposium “Innovation Ecosystems for AI-Based Education, Training and Learning” Paulo Blikstein, Assistant Professor, ...

Machine Learning vs Deep Learning vs Artificial Intelligence | ML vs DL vs AI | Simplilearn

This Machine Learning vs Deep Learning vs Artificial Intelligence video will help you understand the differences between ML, DL and AI, and how they are ...

Introduction to Deep Learning: Machine Learning vs Deep Learning

MATLAB for Deep Learning: Learn about the differences between deep learning and machine learning in this MATLAB® Tech Talk

Yann LeCun: "Deep Learning and the Future of Artificial Intelligence”

Green Family Lecture Series 2018 "Deep Learning and the Future of Artificial Intelligence” Yann LeCun, New York University & Director of AI Research, ...

A.I. Is a Big Fat Lie – The Dr. Data Show

Is AI legit? In this must-see episode of The Dr. Data Show, Eric Siegel delivers a treatise that ridicules the widespread myth of artificial intelligence.

Obstacles to Progress in Deep Learning & AI - Yann LeCun

Feb 20th, 2018 Yann LeCun is a professor at New York University and the Director of AI Research at Facebook.

The Great AI Debate - NIPS2017 - Yann LeCun

The first ever debate at a Neural Information Processing Systems conference. Position: Interpetability is necessary for machine learning For: Rich Caruana, ...