All Quotes

"That even gave us more determination and made us resolute to fight for the benefit of the citizens."

"When we're entrusted with leadership, we're entrusted with responsibility to make change where change needs to be made."

"I don’t know why Ugandans congratulate people on government jobs."

"It’s not a privilege. It’s a responsibility. I’m not one to celebrate appointments."

"would rather celebrate when I have finished my assignment well and people are appreciative of what I have done."

"I think it is a Baganda thing where people think “Ogudde mu bintu."

"That you are suddenly going to get rich."

"You lose money by being in public service."

"You lose business, you lose your social engagements."

"It’s a sacrifice because you don’t have time do something else."

"My take home is about Shs21m. That is after tax, so it cannot be 46m with taxes inclusive. Because people are so used to saying I get 46m, maybe someone should give it to me."

"She doesn’t realize the seriousness of her actions. She understands she has a problem, says she wants to get help, but I have to make sure she actually does."

"I couldn’t sleep anymore because I felt she was in danger."

"Drugs are changing her, she is sliding towards the abyss. To save her, the only way is to hospitalize her."

"There was a period when I was bulimic."

"Women; pregnancy and baby-caring; adventrous."

"Let me tell you girl-childs; frequent birth-giving I did.. As I bow down I summed up; nine years; ten children. I bore Sa'a and the Sa'adu; I have Jamila and Jamilu; I bore Habi and then Habibu; I know Amiru and I know Hamza; I born Basiru and Basiru; remain Saratu and then Saleh..."

"Girl childs; do as you bid; Because one day it will just be a story..."

"In the world, everyone has his hero.."

"I have being insulted; My mother inlaw insults me. My father-inlaw talks throughout the nights. Problems starts with us... If I talk he slaps me.."

"Tell Hajiya Barmani, there is her song, which I see the song is true. which she said; it is only with adornment that woman can become stylish. If there is no adornment how can she become attractive."

"“I want to make it clear that I love Neapolitans and Naples. I have a daughter who is half Neapolitan. I didn’t like being called a racist. The same thing happened with the Malena story. I was publicly shamed for the things I said.”"

"“Mia had always been cheerful, full of life. Then I started noticing the first signs… and I realized that silent monster was taking her away too. […] I would have taken that pain in her place if I could.”"

"“I’m the result of a rape, but after many years I forgave my father and I don’t want to talk about it anymore, also out of respect for my sister who suffers every time it’s brought up.”"

"“You don’t know this, but when you ask for an early bonfire (on Temptation Island), they take you to a hotel… and from there you can't leave! You’re locked in a room and have to stay there until the whole show is over. The days never end.”"

"“The field of deep learning is primarily concerned with how to build computer systems that are able to successfully solve tasks requiring intelligence, while the field of computational neuroscience is primarily concerned with building more accurate models of how the brain actually works.”"

"“∑x∈xP(x) = 1. We refer to this property as being normalized. Without this property, we could obtain probabilities greater than one by computing the probability of one of many events occurring.”"

"“Probability mass functions can act on many variables at the same time. Such a probability distribution over many variables is known as a joint probability distribution. P(x = x, y = y) denotes the probability that x = x and y = y simultaneously. We may also write P(x, y) for brevity.”"

"“one of the names that deep learning has gone by is artificial neural networks (ANNs).”"

"“We assume familiarity with programming, a basic understanding of computational performance issues, complexity theory, introductory level calculus and some of the terminology of graph theory.”"

"“we do not yet know enough about biological learning for neuroscience to offer much guidance for the learning algorithms we use to train these architectures.”"

"“Several key concepts arose during the connectionism movement of the 1980s that remain central to today’s deep learning. One of these concepts is that of distributed representation (Hinton et al., 1986). This is the idea that each input to a system should be represented by many features, and each feature should be involved in the representation of many possible inputs.”"

"“Another major accomplishment of the connectionist movement was the successful use of back-propagation to train deep neural networks with internal representations and the popularization of the back-propagation algorithm (Rumelhart et al., 1986a; LeCun, 1987). This algorithm has waxed and waned in popularity but, as of this writing, is the dominant approach to training deep models.”"

"“Cognitive science is an interdisciplinary approach to understanding the mind, combining multiple different levels of analysis.”"

"“At this point, deep networks were generally believed to be very difficult to train. We now know that algorithms that have existed since the 1980s work quite well, but this was not apparent circa 2006. The issue is perhaps simply that these algorithms were too computationally costly to allow much experimentation with the hardware available at the time.”"

"“Logic provides a set of formal rules for determining what propositions are implied to be true or false given the assumption that some other set of propositions is true or false. Probability theory provides a set of formal rules for determining the likelihood of a proposition being true given the likelihood of other propositions.”"

"“Hochreiter and Schmidhuber (1997) introduced the long short-term memory (LSTM) network to resolve some of these difficulties. Today, the LSTM is widely used for many sequence modeling tasks, including many natural language processing tasks at Google.”"

"“Working successfully with datasets smaller than this is an important research area, focusing in particular on how we can take advantage of large quantities of unlabeled examples, with unsupervised or semi-supervised learning.”"

"“A probability distribution over discrete variables may be described using a probability mass function (PMF).”"

"“Another crowning achievement of deep learning is its extension to the domain of reinforcement learning. In the context of reinforcement learning, an autonomous agent must learn to perform a task by trial and error, without any guidance from the human operator. DeepMind demonstrated that a reinforcement learning system based on deep learning is capable of learning to play Atari video games, reaching human-level performance on many tasks”"

"“Even today’s networks, which we consider quite large from a computational systems point of view, are smaller than the nervous system of even relatively primitive vertebrate animals like frogs.”"

"“The central idea in connectionism is that a large number of simple computational units can achieve intelligent behavior when networked together.”"

"Most of this printout was analysis from the Kotok program. And I also saw some kind of a textual thing, which I don’t believe was Kotok’s thesis, but which had some of the same information as Kotok’s thesis. It was probably some kind of a technical report, or something, that was anticipatory to Kotok’s thesis [2]. Anyway, one of the things I remembered, and which I just talked with Kotok, as a matter of fact, a few days ago, was the detail that they had is Alpha Beta, and so forth, and they had these whips, and the whips were set at 4, 4, 3, 3, 2, 2, 1, 1. In other words, that was how many. It would first look at the top ply. It would look at the four best moves. The next plys, it would look at the three best. Next ply, two best, next ply, one best. Well, I just recognized immediately that that was incredibly wrong."

"You see, basically looking at only one wide, you just have no signals or noise function. In other words, you look at one move, which you think is the best, but there’s a tremendous amount of noise. Well, you look at some more moves, and if you find that one of those are better, you’ve effectively rejected some noise. Well, essentially the thing that I knew that they did, they were very weak chess players, both McCarthy and Kotok. And basically they had a very romanticized view of chess. And so I knew, however, that chess is a very, very precise game. And you really- the name of the game is take the other guy’s pieces, and you don’t just go along. In any kind of a strong game, you don’t just lose pieces, win pieces, lose pieces, win pieces. I mean, if you lose even a single pawn without compensation, then you may have drawing chances, if you’re lucky. Otherwise, the game is lost. Losing more than one pawn almost invariably results in loss of the game, period."

"I was operating as a person intrigued by mechanism rather than concerned with the task, concerned with the problem and the need to bring a solution to the problem"

"Like many students in the intervening years, I was obsessed by this new representational idea and looking for a place to apply it, rather than the other way around - facing the problem and bringing the right tools to bear on it."

"In any event I was speculating on the use of semantic nets in a blocks world context and a very obscure footnote in my thesis proposal said, "Well, gee, if I can describe block structures as semantic nets, then perhaps I could gain something from the differences between two descriptions of different scenes and their semantic net form and that might be a basis for learning something." And maybe I gave an example or something."

"I should refine my notion of how difficult to approach... Minsky has never been difficult to approach. He just seemed that way because anybody sufficiently famous will seem difficult to approach to a shy graduate student. I'm still awed by Minsky. In a sense, nothing's changed."

"I had hoped the weakness in my leg would be treatable, but my doctor shook his head. The intravenous immunoglobulin treatments he'd been giving me for a possible motor neuropathy weren't working, leading him to conclude I had "probable ALS.""

"knew little about the disease, commonly known as Lou Gehrig's disease. I asked, "Do people die?" He looked away and said, "Sometimes." I started to cry, knowing that "sometimes" meant "always." How could I have this awful disease? I ate healthy, exercised, was thin and was rarely sick."