'We're creating alien beings and the reality is we only have a couple of years to adapt to that' computer scientist Geoffrey Hinton in Toronto, Ontario. AI godfather Geoffrey Hinton: Trump is'corrupt, senile felon' who knows nothing about AI'We're creating alien beings and the reality is we only have a couple of years to adapt to that' computer scientist Geoffrey Hinton in Toronto, Ontario. Pioneering computer scientist on why Trump is using'superintelligence' wrong, whether AI could wipe out humanity - and how our biggest challenge will be accepting we're not the only intelligent beings Donald Trump is a "corrupt, senile felon" whose fixation on the term superintelligence proves he knows nothing about AI, said Geoffrey Hinton, "godfather" of the technology, in a wide-ranging interview where he doubled down on recent warnings that AI models pose an existential threat to humanity and scoffed at claims the industry could regulate itself. The pioneering computer scientist, whose work helped lay the foundations of modern AI, has since become one of the technology's most vocal critics. His latest remarks come after a tumultuous month during which a growing list of senior AI scientists and researchers have joined Hinton in ringing the alarm about how the technology he helped create could ultimately escape human control, sparking an industry crisis, the hasty assembly of congressional meetings and a rare global consensus that something must be done.

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?

Sen. Bernie Sanders has called for a ban on superintelligence as AI experts warn Congress may have a year or less to act before a major crisis unfolds.

In this work, we propose an infinite restricted Boltzmann machine (RBM), whose maximum likelihood estimation (MLE) corresponds to a constrained convex optimization. We consider the Frank-Wolfe algorithm to solve the program, which provides a sparse solution that can be interpreted as inserting a hidden unit at each iteration, so that the optimization process takes the form of a sequence of finite models of increasing complexity. As a side benefit, this can be used to easily and efficiently identify an appropriate number of hidden units during the optimization. The resulting model can also be used as an initialization for typical state-of-the-art RBM training algorithms such as contrastive divergence, leading to models with consistently higher test likelihood than random initialization.

In this work, we propose a novel and surprisingly simple routing strategy called self-routing, where each capsule is routed independently by its subordinate routing network. Therefore, the agreement between capsules is not required anymore, but both poses and activations of upper-level capsules are obtained in a way similar to Mixture-of-Experts. Our experiments on CIFAR10, SVHN, and SmallNORB showthat the self-routing performs more robustly against white-box adversarial attacks and affine transformations, requiring less computation.

We introduce a principled approach for unsupervised structure learning of deep neural networks.

And we propose end-to-end training and testing algorithms for this new architecture. Compared to classical neural nets with softmax function as output activation, the surrogate with interpolating function as output activation combines advantages of both deep and manifold learning.

Howe updated 3] using isunkno internal predictions prediction) 4-7].

CP decomposition compresses an input tensor into a sum of rank-one components, and Tucker decomposition approximates an input tensor by a core tensor multiplied by matrices. To date, matrix and tensor decomposition has been extensively analyzed, and there are a number of variations of such decomposition (Kolda and Bader, 2009), where the common goal is to approximate a given tensor by a smaller number of components, or parameters,inanefficientmanner. However, despite the recent advances of decomposition techniques, a learning theory that can systematically define decomposition for any order tensors including vectors and matrices is still under development. Moreover, it is well known that CP and Tucker tensor decomposition include non-convex optimization and that the global convergence is not guaranteed.