Deep learning (deep machine learning, or deep structured learning, or hierarchical learning, or sometimes DL) is a branch ofmachine learning based on a set of algorithms that attempt to model high-level abstractions in data by using multiple processing layers with complex structures or otherwise, composed of multiple non-linear transformations.
Deep learning is part of a broader family of machine learning methods based on learning representations of data. An observation (e.g., an image) can be represented in many ways such as a vector of intensity values per pixel, or in a more abstract way as a set of edges, regions of particular shape, etc.. Some representations make it easier to learn tasks (e.g., face recognition or facial expression recognition) from examples. One of the promises of deep learning is replacing handcrafted features with efficient algorithms for unsupervised or semi-supervised feature learning and hierarchical feature extraction.
Research in this area attempts to make better representations and create models to learn these representations from large-scale unlabeled data. Some of the representations are inspired by advances in neuroscience and are loosely based on interpretation of information processing and communication patterns in a nervous system, such as neural coding which attempts to define a relationship between various stimuli and associated neuronal responses in the brain.
Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks andrecurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks.
Alternatively, deep learning has been characterized as a buzzword, or a rebranding of neural networks.
by STEVEN NOVELLA on Dec 17 2012
We all make decisions every day. I started out my day deciding what to wear, following by a decision of what to write about for this morning’s blog post. Most decisions are small and likely have insignificant consequences, but even small decisions can have a large cumulative effect. Some decisions are huge and can have dramatic effects on the course of our lives or the lives of others. Studying human decision-making, therefore, seems to be a useful endeavor, one likely to have implications for critical thinking.
The current dominant model of decision making is the so-called dual-process approach. Decision-making is seen as coming in two flavors: intuitive-affective, or system I, decision-making is based upon our “gut-feelings”, while analytical system II processing is based upon careful analysis. There are advantages and disadvantages to both, and researchers are busy trying to sort out which approach is superior in which circumstances.
Intuitive decision-making has the advantage of being quick. We get an overall feeling for a situation, based upon evolved emotions and heuristics and modified by our own experiences, and can act quickly on such feelings. The disadvantage of this approach is that it is highly susceptible to bias and may not properly weigh important details. The analytic approach has the advantage of being detail-oriented, logical, and quantitative and can be highly evidence-based, given a statistically accurate weight to each factor considered. The analytic approach is specifically designed to weed out bias and faulty thinking. The disadvantage of the analytic approach is that it is time and effort intensive, and it is only as good as the evidence that feeds into it.