Deep learning for computer vision: a comparison between convolutional neural networks and hierarchical temporal memories on object recognition tasks

In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general. However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of "intelligence". The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them. CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems. HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain. In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.

Mechanochemical solvent-free synthesis of Sn-β Zeolite and Ag2O/TiO2 catalysts

Preparations of heterogeneous catalysts are usually complex processes that involve several procedures as precipitation, crystallization and hydrothermal treatments. This processes are really dependent by the operative conditions such as temperature, pH, concentration etc. Hence the resulting product is extremely affected by any possible variations in these parameters making this synthesis really fragile. With the aim to improve these operations has been decided to exploit a new possible strong environment-respectful process by mechanochemical treatment, which permits to carry out solvent free-solvent synthesis exploiting the Mixer Mill MM400 (Retsch) in order to have reproducible results. Two different systems have been studied in this kind of synthesis: a tin β -zeolite tested in a H-trasnfer reaction of cyclohexanone and a silver on titania catalyst used in the fluorination of 2,2 dimethyl glucaric acid. Each catalyst has been characterized by different techniques in order to understand the transformations involved in the mechanochemical treatment.