Joshua

Joshua /ˈdʒɒʃuə/ or Jehoshua (Hebrew: יְהוֹשֻׁעַ Yĕhôshúʿa or Hebrew: יֵשׁוּעַ Yĕshúʿa; Aramaic: ܝܫܘܥ‎ Isho; Greek: Ἰησοῦς, Arabic: يوشع بن نون‎ Yūshaʿ ibn Nūn; Latin: Iosue, Turkish: Yuşa), is a figure in the Torah, being one of the spies for Israel (Num 13–14) and identified in several passages as Moses' assistant. He is the central figure in the Hebrew Bible's Book of Joshua. According to the books of Exodus, Numbers and Joshua, he became the leader of the Israelite tribes after the death of Moses. His name was Hoshe'a (הוֹשֵׁעַ) the son of Nun, of the tribe of Ephraim, but Moses called him Yehoshu'a (יְהוֹשֻעַ; Joshua in English) (Numbers 13:16) the name by which he is commonly known. The name is shortened to Yeshua in Nehemiah (Nehemiah 8:17). According to the Bible he was born in Egypt prior to the Exodus.

He was one of the twelve spies of Israel sent by Moses to explore the land of Canaan. (Numbers 13:1-16) After the death of Moses, he led the Israelite tribes in the conquest of Canaan, and allocated the land to the tribes. According to Biblical chronology, Joshua lived between 1355-1245 BCE, or sometime in the late Bronze Age. According to Joshua 24:29, Joshua died at the age of 110.

Yoshua Bengio

Yoshua Bengio (born 1964) is a French-born Canadian computer scientist, most noted for his work on artificial neural networks. He is noted for his work in deep learning, along with Yann LeCun, Geoffrey Hinton, Andrew Ng et al. He attended McGill University and was a post-doctoral fellow at MIT and AT&T Bell Labs. He is faculty at the Université de Montréal since 1993. He was a post doc in the Michael I Jordan group.

References

Deep learning

Deep learning (deep structured learning, hierarchical learning or deep machine learning) is a branch of machine 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.