Artificial Intelligence (Neural Networks)

What machines are still NOT good at:

-Learning from small number of examples and less practice -Solving multiple tasks simultaneously -Holding conversations -Active learning -Scene understanding -Language acquisition -Common sense -Feelings -Consciousness -Theory of Mind (understanding thought and intentions of others) -Learning-to-learn -Creativity

components of Human Intelligence:

-perception,self-awareness -learning -ability to use reason and logic -ability to write and speak clearly, use language -behavior in social situations -ability to recognize, understand and deal with people, objects, and symbols -ability to think on the spot and solve novel problems (intuition)

Artificial Neural Network Structure Summary

1. Composed of many units (similar to neurons) 2. Units are interconnected (similar to synapses) 3. Units occupy separate connected layers (similar to multiple brain regions in sensory pathways) 4. Units in deeper layers respond to more and more abstract information (similar to more complex receptive fields in "higher" cortical areas) 5. Require learning to perform tasks efficiently (similar to neural plasticity) 6. Through experience, Artificial Neural Networks learn to recognize patterns .

Turing test

A test to empirically determine whether a computer has achieved intelligence

Artificial Neural Networks make interesting mistakes even after training:

Human brains are much more complex and have many more neurons so context is more apparent

What is Artificial Intelligence

The study of computer systems that attempt to model and apply the intelligence of the human mind

neural networks

are software systems that can train themselves to make sense of the human world.

Scientists that use Artificial Neural Networks:

• Computer scientists (information processing and learning, image classification, object detection and recognition) • Statisticians (classification) • Engineers (signal processing and autonomic control) • Physicists (statistical mechanics) • Biologists (predicting protein shape from mRNA sequences, disorder diagnostic, personalised medicine) • Philosophers (Minds and Machines) • Cognitive scientists (models of thinking, learning and cognition) • Neuro-physiologists (understanding sensory systems and memory)